void computehist(IplImage* image, CvRect roi,cv::MatND* hist,int hbins = 40,int sbins = 40)
{
IplImage* temp = crop( image, roi);
//cv::namedWindow( "bitch face", 1 );
//cv::Mat test(image);
//cv::imshow("bitch face",test);
cv::Mat src(temp);
cv::Mat hsv;
cvtColor(src, hsv, CV_BGR2HSV);
// let's quantize the hue to 30 levels
// and the saturation to 32 levels
int currHistsize[] = {hbins, sbins};
// hue varies from 0 to 179, see cvtColor
float hranges[] = { 0, 180 };
// saturation varies from 0 (black-gray-white) to
// 255 (pure spectrum color)
float sranges[] = { 0, 256 };
const float* ranges[] = { hranges, sranges };
//cv::MatND localhist;
// we compute the histogram from the 0-th and 1-st channels
int channels[] = {0, 1};
calcHist( &hsv, 1, channels, cv::Mat(), // do not use mask
*hist, 2, currHistsize, ranges,
true, // the histogram is uniform
false );
//drawHist(*hist);
}
void MainWindow::on_actionHistogram_equalization_triggered()
{
QPixmap pixmap = pixmapItem->pixmap().copy();
QImage image = pixmap.toImage();
int width = image.width();
int height = image.height();
if (width == 0 || height == 0)
{
ui->statusBar->showMessage( tr("Error. Image bad size"), 3000 );
return;
}
DialogHistogramEqualization dialog;
if (dialog.exec() == QDialog::Rejected)
return;
int equalizationType = dialog.getEqualizationType();
if (equalizationType == 1)
RGB_equalization(image);
else if (equalizationType == 2)
V_equalization(image);
else if (equalizationType == 3)
Grayscale_equalization(image);
pixmap.convertFromImage(image);
pixmapItem_2->setPixmap(pixmap);
scene_2->setSceneRect(QRectF(pixmap.rect()));
calcHist(pixmap, hist_2, maxLevel_2);
drawHist(pixmapItem_4, hist_2, maxLevel_2);
}
void MeanShiftDemo( VideoCapture& video, Rect& starting_position, int starting_frame_number, int end_frame)
{
bool half_size = true;
video.set(CV_CAP_PROP_POS_FRAMES,starting_frame_number);
Mat current_frame, hls_image;
std::vector<cv::Mat> hls_planes(3);
video >> current_frame;
Rect current_position(starting_position);
if (half_size)
{
resize(current_frame, current_frame, Size( current_frame.cols/2, current_frame.rows/2 ));
current_position.height /= 2;
current_position.width /= 2;
current_position.x /= 2;
current_position.y /= 2;
}
cvtColor(current_frame, hls_image, CV_BGR2HLS);
split(hls_image,hls_planes);
int chosen_channel = 0; // Hue channel
Mat image1ROI = hls_planes[chosen_channel](current_position);
float channel_range[2] = { 0.0, 255.0 };
int channel_numbers[1] = { 0 };
int number_bins[1] = { 32 };
MatND histogram[1];
const float* channel_ranges = channel_range;
calcHist(&(image1ROI), 1, channel_numbers, Mat(), histogram[0], 1 , number_bins, &channel_ranges);
normalize(histogram[0],histogram[0],1.0);
rectangle(current_frame,current_position,Scalar(0,255,0),2);
Mat starting_frame = current_frame.clone();
int frame_number = starting_frame_number;
while (!current_frame.empty() && (frame_number < end_frame))
{
// Calculate back projection
Mat back_projection_probabilities;
calcBackProject(&(hls_planes[chosen_channel]),1,channel_numbers,*histogram,back_projection_probabilities,&channel_ranges,255.0);
// Remove low saturation points from consideration
Mat saturation_mask;
inRange( hls_image, Scalar(0,10,50,0),Scalar(180,256,256,0), saturation_mask );
bitwise_and( back_projection_probabilities, back_projection_probabilities,back_projection_probabilities, saturation_mask );
// Mean shift
TermCriteria criteria(cv::TermCriteria::MAX_ITER,5,0.01);
meanShift(back_projection_probabilities,current_position,criteria);
// Output to screen
rectangle(current_frame,current_position,Scalar(0,255,0),2);
Mat chosen_channel_image, back_projection_image;
cvtColor(hls_planes[chosen_channel], chosen_channel_image, CV_GRAY2BGR);
cvtColor(back_projection_probabilities, back_projection_image, CV_GRAY2BGR);
Mat row1_output = JoinImagesHorizontally( starting_frame, "Starting position", chosen_channel_image, "Chosen channel (Hue)", 4 );
Mat row2_output = JoinImagesHorizontally( back_projection_image, "Back projection", current_frame, "Current position", 4 );
Mat mean_shift_output = JoinImagesVertically(row1_output,"",row2_output,"", 4);
imshow("Mean Shift Tracking", mean_shift_output );
// Advance to next frame
video >> current_frame;
if (half_size)
resize(current_frame, current_frame, Size( current_frame.cols/2, current_frame.rows/2 ));
cvtColor(current_frame, hls_image, CV_BGR2HLS);
split(hls_image,hls_planes);
frame_number++;
cvWaitKey(1000);
}
char c = cvWaitKey();
cvDestroyAllWindows();
}
double cv::calcGlobalOrientation( InputArray _orientation, InputArray _mask,
InputArray _mhi, double /*timestamp*/,
double duration )
{
Mat orient = _orientation.getMat(), mask = _mask.getMat(), mhi = _mhi.getMat();
Size size = mhi.size();
CV_Assert( mask.type() == CV_8U && orient.type() == CV_32F && mhi.type() == CV_32F );
CV_Assert( mask.size() == size && orient.size() == size );
CV_Assert( duration > 0 );
int histSize = 12;
float _ranges[] = { 0.f, 360.f };
const float* ranges = _ranges;
Mat hist;
calcHist(&orient, 1, 0, mask, hist, 1, &histSize, &ranges);
// find the maximum index (the dominant orientation)
Point baseOrientPt;
minMaxLoc(hist, 0, 0, 0, &baseOrientPt);
float fbaseOrient = (baseOrientPt.x + baseOrientPt.y)*360.f/histSize;
// override timestamp with the maximum value in MHI
double timestamp = 0;
minMaxLoc( mhi, 0, ×tamp, 0, 0, mask );
// find the shift relative to the dominant orientation as weighted sum of relative angles
float a = (float)(254. / 255. / duration);
float b = (float)(1. - timestamp * a);
float delbound = (float)(timestamp - duration);
if( mhi.isContinuous() && mask.isContinuous() && orient.isContinuous() )
{
size.width *= size.height;
size.height = 1;
}
/*
a = 254/(255*dt)
b = 1 - t*a = 1 - 254*t/(255*dur) =
(255*dt - 254*t)/(255*dt) =
(dt - (t - dt)*254)/(255*dt);
--------------------------------------------------------
ax + b = 254*x/(255*dt) + (dt - (t - dt)*254)/(255*dt) =
(254*x + dt - (t - dt)*254)/(255*dt) =
((x - (t - dt))*254 + dt)/(255*dt) =
(((x - (t - dt))/dt)*254 + 1)/255 = (((x - low_time)/dt)*254 + 1)/255
*/
float shiftOrient = 0, shiftWeight = 0;
for( int y = 0; y < size.height; y++ )
{
const float* mhiptr = mhi.ptr<float>(y);
const float* oriptr = orient.ptr<float>(y);
const uchar* maskptr = mask.ptr<uchar>(y);
for( int x = 0; x < size.width; x++ )
{
if( maskptr[x] != 0 && mhiptr[x] > delbound )
{
/*
orient in 0..360, base_orient in 0..360
-> (rel_angle = orient - base_orient) in -360..360.
rel_angle is translated to -180..180
*/
float weight = mhiptr[x] * a + b;
float relAngle = oriptr[x] - fbaseOrient;
relAngle += (relAngle < -180 ? 360 : 0);
relAngle += (relAngle > 180 ? -360 : 0);
if( fabs(relAngle) < 45 )
{
shiftOrient += weight * relAngle;
shiftWeight += weight;
}
}
}
}
// add the dominant orientation and the relative shift
if( shiftWeight == 0 )
shiftWeight = 0.01f;
fbaseOrient += shiftOrient / shiftWeight;
fbaseOrient -= (fbaseOrient < 360 ? 0 : 360);
fbaseOrient += (fbaseOrient >= 0 ? 0 : 360);
return fbaseOrient;
}
void FindObjectMain::process_camshift()
{
// Some user defined parameters
int vmin = config.vmin;
int vmax = config.vmax;
int smin = config.smin;
float hranges[] = { 0, 180 };
const float* phranges = hranges;
// Create aligned, RGB images
if(!object_image)
{
object_image = cvCreateImage(
cvSize(object_image_w, object_image_h),
8,
3);
}
if(!scene_image)
{
scene_image = cvCreateImage(
cvSize(scene_image_w, scene_image_h),
8,
3);
}
// Temporary row pointers
unsigned char **object_rows = new unsigned char*[object_image_h];
unsigned char **scene_rows = new unsigned char*[scene_image_h];
for(int i = 0; i < object_image_h; i++)
{
object_rows[i] = (unsigned char*)(object_image->imageData + i * object_image_w * 3);
}
for(int i = 0; i < scene_image_h; i++)
{
scene_rows[i] = (unsigned char*)(scene_image->imageData + i * scene_image_w * 3);
}
// Transfer object & scene to RGB images for OpenCV
if(!prev_object) prev_object = new unsigned char[object_image_w * object_image_h * 3];
// Back up old object image
memcpy(prev_object, object_image->imageData, object_image_w * object_image_h * 3);
BC_CModels::transfer(object_rows,
get_input(object_layer)->get_rows(),
0,
0,
0,
0,
0,
0,
object_x1,
object_y1,
object_w,
object_h,
0,
0,
object_w,
object_h,
get_input(object_layer)->get_color_model(),
BC_RGB888,
0,
0,
0);
BC_CModels::transfer(scene_rows,
get_input(scene_layer)->get_rows(),
0,
0,
0,
0,
0,
0,
scene_x1,
scene_y1,
scene_w,
scene_h,
0,
0,
scene_w,
scene_h,
get_input(scene_layer)->get_color_model(),
BC_RGB888,
0,
0,
0);
delete [] object_rows;
delete [] scene_rows;
// from camshiftdemo.cpp
// Compute new object
if(memcmp(prev_object,
object_image->imageData,
object_image_w * object_image_h * 3) ||
!hist.dims)
{
Mat image(object_image);
Mat hsv, hue, mask;
cvtColor(image, hsv, CV_RGB2HSV);
int _vmin = vmin, _vmax = vmax;
//printf("FindObjectMain::process_camshift %d\n", __LINE__);
inRange(hsv,
Scalar(0, smin, MIN(_vmin,_vmax)),
Scalar(180, 256, MAX(_vmin, _vmax)),
mask);
int ch[] = { 0, 0 };
hue.create(hsv.size(), hsv.depth());
mixChannels(&hsv, 1, &hue, 1, ch, 1);
Rect selection = Rect(0, 0, object_w, object_h);
trackWindow = selection;
int hsize = 16;
Mat roi(hue, selection), maskroi(mask, selection);
calcHist(&roi, 1, 0, maskroi, hist, 1, &hsize, &phranges);
normalize(hist, hist, 0, 255, CV_MINMAX);
}
// compute scene
Mat image(scene_image);
Mat hsv, hue, mask, backproj;
cvtColor(image, hsv, CV_RGB2HSV);
int _vmin = vmin, _vmax = vmax;
inRange(hsv,
Scalar(0, smin, MIN(_vmin,_vmax)),
Scalar(180, 256, MAX(_vmin, _vmax)),
mask);
int ch[] = {0, 0};
hue.create(hsv.size(), hsv.depth());
mixChannels(&hsv, 1, &hue, 1, ch, 1);
//printf("FindObjectMain::process_camshift %d %d %d\n", __LINE__, hist.dims, hist.size[1]);
RotatedRect trackBox = RotatedRect(
Point2f((object_x1 + object_x2) / 2, (object_y1 + object_y2) / 2),
Size2f(object_w, object_h),
0);
trackWindow = Rect(0,
0,
scene_w,
scene_h);
if(hist.dims > 0)
{
calcBackProject(&hue, 1, 0, hist, backproj, &phranges);
backproj &= mask;
//printf("FindObjectMain::process_camshift %d\n", __LINE__);
// if(trackWindow.width <= 0 ||
// trackWindow.height <= 0)
// {
// trackWindow.width = object_w;
// trackWindow.height = object_h;
// }
trackBox = CamShift(backproj,
trackWindow,
TermCriteria( CV_TERMCRIT_EPS | CV_TERMCRIT_ITER, 10, 1 ));
//printf("FindObjectMain::process_camshift %d\n", __LINE__);
// if( trackWindow.area() <= 1 )
// {
// int cols = backproj.cols;
// int rows = backproj.rows;
// int r = (MIN(cols, rows) + 5) / 6;
// trackWindow = Rect(trackWindow.x - r, trackWindow.y - r,
// trackWindow.x + r, trackWindow.y + r) &
// Rect(0, 0, cols, rows);
// }
}
// printf("FindObjectMain::process_camshift %d %d %d %d %d\n",
// __LINE__,
// trackWindow.x,
// trackWindow.y,
// trackWindow.width,
// trackWindow.height);
// Draw mask over scene
if(config.draw_keypoints)
{
for(int i = 0; i < scene_h; i++)
{
switch(get_input(scene_layer)->get_color_model())
{
case BC_YUV888:
{
unsigned char *input = backproj.data + i * scene_image_w;
unsigned char *output = get_input(scene_layer)->get_rows()[i + scene_y1] + scene_x1 * 3;
for(int j = 0; j < scene_w; j++)
{
output[0] = *input;
output[1] = 0x80;
output[2] = 0x80;
output += 3;
input++;
}
break;
}
}
}
}
// Get object outline in the scene layer
// printf("FindObjectMain::process_camshift %d %d %d %d %d %d\n",
// __LINE__,
// (int)trackBox.center.x,
// (int)trackBox.center.y,
// (int)trackBox.size.width,
// (int)trackBox.size.height,
// (int)trackBox.angle);
double angle = trackBox.angle * 2 * M_PI / 360;
double angle1 = atan2(-(double)trackBox.size.height / 2, -(double)trackBox.size.width / 2) + angle;
double angle2 = atan2(-(double)trackBox.size.height / 2, (double)trackBox.size.width / 2) + angle;
double angle3 = atan2((double)trackBox.size.height / 2, (double)trackBox.size.width / 2) + angle;
double angle4 = atan2((double)trackBox.size.height / 2, -(double)trackBox.size.width / 2) + angle;
double radius = sqrt(SQR(trackBox.size.height / 2) + SQR(trackBox.size.width / 2));
border_x1 = (int)(trackBox.center.x + cos(angle1) * radius) + scene_x1;
border_y1 = (int)(trackBox.center.y + sin(angle1) * radius) + scene_y1;
border_x2 = (int)(trackBox.center.x + cos(angle2) * radius) + scene_x1;
border_y2 = (int)(trackBox.center.y + sin(angle2) * radius) + scene_y1;
border_x3 = (int)(trackBox.center.x + cos(angle3) * radius) + scene_x1;
border_y3 = (int)(trackBox.center.y + sin(angle3) * radius) + scene_y1;
border_x4 = (int)(trackBox.center.x + cos(angle4) * radius) + scene_x1;
border_y4 = (int)(trackBox.center.y + sin(angle4) * radius) + scene_y1;
}
// main function in class ColorGroup
// analyze and classify images
void ColorGroup::run(){
int i;
// colors = (string*)malloc(sizeof(string)*num);
// temporary buffer (additional function that changes the size of buffer is needed)
string colors[100];
// make the folder to save the result
makecolorfolder();
// for each image,
for(i=0; i<num; i++){
Mat image, hsv_image;
image = images[i];
// extract color element of the image
// if the images doesn't have 3 channels, it's classified to 'etc'
if (image.channels() == 3){
// change the mode of image from RGB to HSV
cvtColor(image, hsv_image, CV_BGR2HSV);
// Separate the image in 3 places ( H, S, V )
vector<Mat> hsv_planes;
split( hsv_image, hsv_planes );
// make histogram with color element ('h' in hsv means 'hue')
int hHistSize = 180;
float hRange[] = {0, 180}, vRange[] = {0, 100};
const float* hHistRange = { hRange };
Mat h_hist;
calcHist( &hsv_planes[0], 1, 0, Mat(), h_hist, 1, &hHistSize, &hHistRange, true, false);
int hHist_w = 360; int hHist_h = 400;
int hbin_w = cvRound( (double) hHist_w/hHistSize);
Mat hHistImage( hHist_h, hHist_w, CV_8UC3, Scalar( 0, 0, 0) );
normalize(h_hist, h_hist, 0, hHistImage.rows, NORM_MINMAX, -1, Mat() );
// with histogram of color, get the most used color
colors[i] = mostUsedColor(h_hist, hHistSize);
cout << "most used color is " << colors[i] << endl;
} else {
colors[i] = "etc";
}
}
// with the color array result, classify and save images in appropriate folder
if( flag == IS_FROM_FILES ){
int i=0;
string filename;
// open "filenames.txt" and get the name of file
ifstream file;
file.open("filenames.txt");
// save the images in appropriate folder which is the color array result
while(!file.eof() && i<num ){
getline(file, filename);
char newfile[FILE_NAME_MAX+20] = "./color_result/";
strcat(newfile, colors[i].c_str());
strcat(newfile, "/");
strcat(newfile, filename.c_str());
cout << "new file adress : " << newfile << endl;
imwrite(newfile, images[i]);
i++;
}
}else if( flag == IS_FROM_URLS ){
int i;
// make the file name to save. It counts from 0 in increasing order
// and save the images in appropriate folder which is the color array result
const char file[10] = "photo_";
for( i=0; i<num; i++){
char newfile[FILE_NAME_MAX+20] = "./color_result/";
strcat(newfile, colors[i].c_str());
strcat(newfile, "/");
strcat(newfile, file);
if( i < 10 ){
strcat(newfile, "00");
strcat(newfile, intToString(i).c_str());
}else if ( i >= 10 && i < 100 ){
strcat(newfile, "0");
strcat(newfile, intToString(i).c_str());
}else if ( i >= 100 && i < 1000 ){
strcat(newfile, intToString(i).c_str());
}
cout << newfile << endl;
strcat(newfile, ".jpg");
imwrite(newfile, images[i]);
}
}
cout << "color grouping finished" << endl;
}
CvPoint2D32f getPupilCenter(Mat &eye_box){
//find x and y gradients
Mat gradientX = computeGradient(eye_box);
Mat gradientY = computeGradient(eye_box.t()).t();
//normalize and threshold the gradient
Mat mags = matrixMagnitude(gradientX, gradientY);
//create a blurred and inverted image for weighting
Mat weight;
bitwise_not(eye_box, weight);
blur(weight, weight, Size(2,2));
//weight the magnitudes, convert to 8-bit for thresholding
weight.convertTo(weight, CV_32F);
mags = mags.mul(weight);
normalize(mags, mags, 0, 1, NORM_MINMAX, CV_32F);
mags.convertTo(mags, CV_8UC1, 255);
//threshold using Otsu's method
threshold(mags, mags, 0, 255, THRESH_BINARY | THRESH_OTSU);
//convert to CV_32S and filter gradients
mags.convertTo(mags, CV_32S);
gradientY = gradientY.mul(mags);
gradientX = gradientX.mul(mags);
//resize arrays to same size
resize(gradientX, gradientX, Size(EYE_FRAME_SIZE, EYE_FRAME_SIZE), 0, 0, INTER_NEAREST);
resize(gradientY, gradientY, Size(EYE_FRAME_SIZE, EYE_FRAME_SIZE), 0, 0, INTER_NEAREST);
resize(weight, weight, Size(EYE_FRAME_SIZE, EYE_FRAME_SIZE), 0, 0, INTER_NEAREST);
//imshow("gradY", gradientY * 255);
//imshow("weight", weight / 255);
//run the algorithm:
// for each possible gradient location
// Note: these loops are reversed from the way the paper does them
// it evaluates every possible center for each gradient location instead of
// every possible gradient location for every center.
Mat out = Mat::zeros(weight.rows,weight.cols, CV_32F);
float max_val = 0;
//for all pixels in the image
for (int y = 0; y < EYE_FRAME_SIZE; ++y) {
const int *grad_x = gradientX.ptr<int>(y), *grad_y = gradientY.ptr<int>(y);
for (int x = 0; x < EYE_FRAME_SIZE; ++x) {
int gX = grad_x[x], gY = grad_y[x];
if (gX == 0 && gY == 0) {
continue;
}
//for all possible centers
for (int cy = 0; cy < EYE_FRAME_SIZE; ++cy) {
float *Or = out.ptr<float>(cy);
const float *Wr = weight.ptr<float>(cy);
for (int cx = 0; cx < EYE_FRAME_SIZE; ++cx) {
//ignore center of box
if (x == cx && y == cy) {
continue;
}
//create a vector from the possible center to the gradient origin
int dx = x - cx;
int dy = y - cy;
//compute dot product using lookup table
float dotProduct;
if(dx > 0 && dy > 0){
dotProduct = dpX[dx+EYE_FRAME_SIZE*dy]*gX + dpY[dx+EYE_FRAME_SIZE*dy]*gY;
}else if(dx > 0){
dotProduct = dpX[dx-EYE_FRAME_SIZE*dy]*gX - dpY[dx-EYE_FRAME_SIZE*dy]*gY;
}else if(dy > 0){
dotProduct = -dpX[-dx+EYE_FRAME_SIZE*dy]*gX - dpY[-dx+EYE_FRAME_SIZE*dy]*gY;
}else{
dotProduct = -dpX[-dx-EYE_FRAME_SIZE*dy]*gX - dpY[-dx-EYE_FRAME_SIZE*dy]*gY;
}
//ignore negative dot products as they point away from eye
if(dotProduct <= 0.0){
continue;
}
//square and multiply by the weight
Or[cx] += dotProduct * dotProduct * Wr[cx];
//compare with max
if(Or[cx] > max_val){
max_val = Or[cx];
}
}
}
}
}
//resize for debugging
resize(out, out, Size(500,500), 0, 0, INTER_NEAREST);
out = 255 * out / max_val;
//imshow("calc", out / 255);
//histogram setup
Mat hist;
int histSize = 256;
float range[] = { 0, 256 } ;
const float* histRange = { range };
//calculate the histogram
calcHist(&out,1, 0, Mat(), hist, 1, &histSize, &histRange,
true, //uniform
true //accumulate
);
//get cutoff for top 10 pixels
float top_end_sum = 0;
int top_end = 0.92 * 255;
for (int i = 255; i > 0; i--) {
top_end_sum += hist.at<float>(i);
if(top_end_sum > 3000){
top_end = i;
break;
}
}
//draw image for debugging
Mat histImage(400, 512, CV_8UC3, Scalar(0,0,0));
int bin_w = cvRound( (double) 512/histSize );
normalize(hist, hist, 0, histImage.rows, NORM_MINMAX, -1, Mat());
/// Draw for each channel
for( int i = 1; i < histSize; i++)
{
line(histImage, Point(bin_w*(i), 400 - cvRound(hist.at<float>(i))),
Point(bin_w*(i), 400),
Scalar(i, i, i), 2, 8, 0);
}
//imshow("hist", histImage);
//threshold to get just the pupil
//printf("top_end: %d\n", top_end);
threshold(out, out, top_end, 255, THRESH_TOZERO);
//calc center of mass
float sum = 0;
float sum_x = 0;
float sum_y = 0;
for (int y = 0; y < out.rows; ++y)
{
float* row = out.ptr<float>(y);
for (int x = 0; x < out.cols; ++x)
{
float val = row[x]*row[x];
if(val > 0){
sum += val;
sum_x += val*x;
sum_y += val*y;
}
}
}
Size eye_box_size = eye_box.size();
Size out_size = out.size();
//cout << "Size1: "+to_string(eye_box_size.width)+","+to_string(eye_box_size.height)+"\n";
//cout << "Size2: "+to_string(out_size.width)+","+to_string(out_size.height)+"\n";
float x_scale = (float) eye_box_size.width / out_size.width;
float y_scale = (float) eye_box_size.height / out_size.height;
CvPoint2D32f max = cvPoint2D32f(x_scale*sum_x/sum, y_scale*sum_y/sum);
//circle(out, max, 3, 0);
//imshow("thresh", out / 255);
return max;
}
int main( int argc, char** argv ) {
/// Load an image
cv::Mat src, greyIm, histeqIm;
src = cv::imread( argv[1] );
if( !src.data ) {
printf("Input file? No? ouuuupsss thooooorryyyyy\n");
return -1;
}
cv::Size s = src.size();
int rows = s.height;
int cols = s.width;
// Setup a rectangle to define your region of interest
cv::Rect myROI(0, rows/2, cols, rows/2);
// Crop the full image to that image contained by the rectangle myROI
// Note that this doesn't copy the data
cv::Mat croppedImage = src(myROI);
cv::imwrite("output/1_low_half.jpg", croppedImage);
cv::cvtColor(croppedImage, greyIm, cv::COLOR_BGR2GRAY);
cv::Size crop_size = croppedImage.size();
int crop_rows = crop_size.height;
int crop_cols = crop_size.width;
cv::imwrite("output/2_grey_scale.jpg", greyIm);
cv::equalizeHist( greyIm, histeqIm );
cv::imwrite("output/3_hist_eq.jpg", histeqIm);
std::vector<std::vector<cv::Point> > contours;
std::vector<cv::Vec4i> hierarchy;
// Reduce noise with kernel 3x3
cv::Mat blurIm;
blur(histeqIm, blurIm, cv::Size(3,3));
cv::imwrite("output/4_blur.jpg", blurIm);
// Canny detector
cv::Mat edgesIm;
Canny(blurIm, edgesIm, thresh, thresh*ratio, kernel_size);
cv::imwrite("output/5_edge.jpg", edgesIm);
// Find contours
cv::findContours(edgesIm, contours, hierarchy, cv::RETR_TREE, cv::CHAIN_APPROX_SIMPLE, cv::Point(0,0));
// Approximate contours to polygons + get bounding rects and circles
std::vector<std::vector<cv::Point> > contours_poly(contours.size());
std::vector<cv::Rect> boundRect(contours.size());
std::vector<cv::Point2f>center(contours.size());
std::vector<float>radius(contours.size());
for (int i = 0; i < contours.size(); i++) {
cv::approxPolyDP(cv::Mat(contours[i]), contours_poly[i], 3, true);
boundRect[i] = cv::boundingRect(cv::Mat(contours_poly[i]));
cv::minEnclosingCircle((cv::Mat)contours_poly[i], center[i], radius[i]);
}
// Draw contours
int j=0;
cv::Mat drawing = cv::Mat::zeros(edgesIm.size(), CV_8UC3);
cv::Mat piece[5], hsvIm[5];
for (int i = 0; i < contours.size(); i++) {
if (!((boundRect[i].height >= boundRect[i].width/5) && (boundRect[i].height <= boundRect[i].width/2)
&& boundRect[i].height<=crop_rows/4 && boundRect[i].width<=crop_cols/2
&& boundRect[i].height>=crop_rows/10 && boundRect[i].width>=crop_cols/6))
continue;
cv::Rect roi = boundRect[i];
piece[j] = croppedImage(roi);
imwrite("output/contour"+std::to_string(j)+".jpg", piece[j]);
j++;
cv::Scalar color = cv::Scalar(rng.uniform(0, 255), rng.uniform(0,255), rng.uniform(0,255));
cv::drawContours(drawing, contours, i, color, 2, 8, hierarchy, 0, cv::Point());
cv::rectangle(drawing, boundRect[i].tl(), boundRect[i].br(), color, 2, 8, 0);
//circle(drawing, center[i], (int)radius[i], color, 2, 8, 0);
}
imwrite("output/6_contours.jpg", drawing);
int h_bins = 50; int s_bins = 60;
int histSize[] = { h_bins, s_bins };
float h_ranges[] = { 0, 180 };
float s_ranges[] = { 0, 256 };
const float* ranges[] = { h_ranges, s_ranges };
int channels[] = { 0, 1 };
cv::Mat hist[5];
for (int i=0; i<j; i++){
cvtColor(piece[i], hsvIm[i], cv::COLOR_BGR2HSV);
imwrite("output/hsvIm"+std::to_string(i)+".jpg", hsvIm[i]);
calcHist( &hsvIm[i], 1, channels, cv::Mat(), hist[i], 2, histSize, ranges, true, false );
//normalize( hsvIm[i], hsvIm[i], 0, 1, cv::NORM_MINMAX, -1, cv::Mat() );
}
return 0;
}
void MainWindow::on_actionOtsu_local_triggered()
{
QPixmap pixmap = pixmapItem->pixmap().copy();
QImage image = pixmap.toImage();
int width = image.width();
int height = image.height();
if (width == 0 || height == 0)
{
ui->statusBar->showMessage( tr("Error. Image bad size"), 3000 );
return;
}
DialogOtsuLocal dialog;
dialog.setSpinBoxes(pixmapItem->pixmap().width(), pixmapItem->pixmap().height());
if (dialog.exec() == QDialog::Rejected)
return;
std::vector<int> grays(width * height, 0);
int countX = dialog.gridX();
int countY = dialog.gridY();
double shiftY = ( (double) height ) / countY;
double shiftX = ( (double) width ) / countX;
double curX = 0.0;
double curY = 0.0;
double nextX = 0.0;
double nextY = 0.0;
int cX;
int cY;
int nX;
int nY;
QRgb black = qRgb(0,0,0);
QRgb white = qRgb(255,255,255);
QRgb newColor;
for (int i = 0; i < countY; ++i)
{
nextY += shiftY;
cY = qFloor(curY);
nY = qFloor(nextY);
curX = 0.0;
nextX = 0.0;
for (int j = 0; j < countX; ++j)
{
nextX += shiftX;
cX = qFloor(curX);
nX = qFloor(nextX);
int threshold = otsu(image, grays, cX, cY, nX, nY);
for (int y = cY; y < nY; ++y)
for (int x = cX; x < nX; ++x)
{
int gray = grays[x + y * (nX - cX)];
if ( gray < threshold )
newColor = black;
else
newColor = white;
image.setPixel(x, y, newColor);
}
curX = nextX;
}
curY = nextY;
}
pixmap.convertFromImage(image);
pixmapItem_2->setPixmap(pixmap);
scene_2->setSceneRect(QRectF(pixmap.rect()));
calcHist(pixmap, hist_2, maxLevel_2);
drawHist(pixmapItem_4, hist_2, maxLevel_2);
}
void MainWindow::on_actionBrightness_gradient_triggered()
{
QPixmap pixmap = pixmapItem->pixmap().copy();
QImage image = pixmap.toImage();
int width = image.width();
int height = image.height();
if (width == 0 || height == 0)
{
ui->statusBar->showMessage( tr("Error. Image bad size"), 3000 );
return;
}
std::vector< std::vector<int> > grays( width, std::vector<int>(height) );
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
QRgb oldColor = image.pixel(x, y);
int gray = qPow(
0.2126 * qPow(qRed(oldColor), 2.2) +
0.7152 * qPow(qGreen(oldColor), 2.2) +
0.0722 * qPow(qBlue(oldColor), 2.2),
1/2.2
);
grays[x][y] = gray;
}
int G_x;
int G_y;
int G;
unsigned long int dividend = 0;
unsigned int divisor = 0;
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
if (x == 0)
G_x = grays[x+1][y];
else if (x == width - 1)
G_x = grays[x-1][y];
else
G_x = grays[x+1][y] - grays[x-1][y];
if (y == 0)
G_y = grays[x][y+1];
else if (y == height - 1)
G_y = grays[x][y-1];
else
G_y = grays[x][y+1] - grays[x][y-1];
G = qMax( qAbs(G_x), qAbs(G_y) );
dividend += grays[x][y] * G;
divisor += G;
}
int threshold = dividend / divisor;
if (0 <= threshold && threshold <= 255)
{
QRgb black = qRgb(0,0,0);
QRgb white = qRgb(255,255,255);
QRgb newColor;
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
int gray = grays[x][y];
if ( gray < threshold )
newColor = black;
else
newColor = white;
image.setPixel(x, y, newColor);
}
}
else
ui->statusBar->showMessage(tr("Error. Invalid threshold"), 3000);
pixmap.convertFromImage(image);
pixmapItem_2->setPixmap(pixmap);
scene_2->setSceneRect(QRectF(pixmap.rect()));
calcHist(pixmap, hist_2, maxLevel_2);
drawHist(pixmapItem_4, hist_2, maxLevel_2);
}
void MainWindow::on_actionZoom_triggered()
{
QPixmap oldPixmap = pixmapItem->pixmap();
QImage oldImage = oldPixmap.toImage();
int oldWidth = oldImage.width();
int oldHeight = oldImage.height();
if (oldWidth == 0 || oldHeight == 0)
{
ui->statusBar->showMessage( tr("Error. Image bad size"), 3000 );
return;
}
DialogZoom dialog;
if (dialog.exec() == QDialog::Rejected)
return;
double value = dialog.getValue();
int choice = dialog.getChoice();
int width = oldWidth * value;
int height = oldHeight * value;
QImage image(width, height, QImage::Format_ARGB32);
image.fill( QColor(255, 255, 255) );
if (choice == 1)
{
for (int i = 0; i < width; ++i)
for (int j = 0; j < height; ++j)
{
int srcX = i / value;
int srcY = j / value;
image.setPixel(i, j, oldImage.pixel(srcX, srcY));
}
}
else if (choice == 2)
{
int h, w;
double t;
double u;
double tmp;
double d1, d2, d3, d4;
QRgb p1, p2, p3, p4;
int red, green, blue;
for (int j = 0; j < height; ++j)
{
tmp = j / (double) (height - 1) * (oldHeight - 1);
h = qFloor(tmp);
h = h < 0? 0: (h >= oldHeight - 1? oldHeight - 2: h);
u = tmp - h;
for (int i = 0; i < width; ++i)
{
tmp = i / (double) (width - 1) * (oldWidth - 1);
w = qFloor(tmp);
w = w < 0? 0: (w >= oldWidth - 1? oldWidth - 2: w);
t = tmp - w;
d1 = (1 - t) * (1 - u);
d2 = t * (1 - u);
d3 = t * u;
d4 = (1 - t) * u;
p1 = oldImage.pixel(w, h);
p2 = oldImage.pixel(w + 1, h);
p3 = oldImage.pixel(w + 1, h + 1);
p4 = oldImage.pixel(w, h + 1);
red = (int)(qRed(p1) * d1) + (int)(qRed(p2) * d2) + (int)(qRed(p3) * d3) + (int)(qRed(p4) * d4);
blue = (int)(qBlue(p1) * d1) + (int)(qBlue(p2) * d2) + (int)(qBlue(p3) * d3) + (int)(qBlue(p4) * d4);
green = (int)(qGreen(p1) * d1) + (int)(qGreen(p2) * d2) + (int)(qGreen(p3) * d3) + (int)(qGreen(p4) * d4);
image.setPixel(i, j, qRgb(red, green, blue));
}
}
}
else if (choice == 3)
{
int scale = qCeil(value);
for (int j = scale; j < height - 2 * value; ++j)
{
// int h = qFloor(j / value);
// h = h < 0? 0: (h >= oldHeight - 1? oldHeight - 2: h);
for (int i = scale; i < width - 2 * value; ++i)
{
// int w = qFloor(i / value);
// w = w < 0? 0: (w >= oldWidth - 1? oldWidth - 2: w);
int srcX = qFloor(i / value);
int srcY = qFloor(j / value);
double relativeX = (i / value) - qFloor((i / value));
double relativeY = (j / value) - qFloor((j / value));
QRgb p00 = oldImage.pixel(srcX - 1, srcY - 1);
QRgb p10 = oldImage.pixel(srcX, srcY - 1);
QRgb p20 = oldImage.pixel(srcX + 1, srcY - 1);
QRgb p30 = oldImage.pixel(srcX + 2, srcY - 1);
QRgb p01 = oldImage.pixel(srcX - 1, srcY);
QRgb p11 = oldImage.pixel(srcX, srcY);
QRgb p21 = oldImage.pixel(srcX + 1, srcY);
QRgb p31 = oldImage.pixel(srcX + 2, srcY);
QRgb p02 = oldImage.pixel(srcX - 1, srcY + 1);
QRgb p12 = oldImage.pixel(srcX, srcY + 1);
QRgb p22 = oldImage.pixel(srcX + 1, srcY + 1);
QRgb p32 = oldImage.pixel(srcX + 2, srcY + 1);
QRgb p03 = oldImage.pixel(srcX - 1, srcY + 2);
QRgb p13 = oldImage.pixel(srcX, srcY + 2);
QRgb p23 = oldImage.pixel(srcX + 1, srcY + 2);
QRgb p33 = oldImage.pixel(srcX + 2, srcY + 2);
double r0 = CubicInterpolation( relativeX, qRed(p00), qRed(p10), qRed(p20), qRed(p30) );
double r1 = CubicInterpolation( relativeX, qRed(p01), qRed(p11), qRed(p21), qRed(p31) );
double r2 = CubicInterpolation( relativeX, qRed(p02), qRed(p12), qRed(p22), qRed(p32) );
double r3 = CubicInterpolation( relativeX, qRed(p03), qRed(p13), qRed(p23), qRed(p33) );
int r = qMax(0.0, qMin(255.0, CubicInterpolation(relativeY, r0, r1, r2, r3)));
double g0 = CubicInterpolation( relativeX, qGreen(p00), qGreen(p10), qGreen(p20), qGreen(p30) );
double g1 = CubicInterpolation( relativeX, qGreen(p01), qGreen(p11), qGreen(p21), qGreen(p31) );
double g2 = CubicInterpolation( relativeX, qGreen(p02), qGreen(p12), qGreen(p22), qGreen(p32) );
double g3 = CubicInterpolation( relativeX, qGreen(p03), qGreen(p13), qGreen(p23), qGreen(p33) );
int g = qMax(0.0, qMin(255.0, CubicInterpolation(relativeY, g0, g1, g2, g3)));
double b0 = CubicInterpolation( relativeX, qBlue(p00), qBlue(p10), qBlue(p20), qBlue(p30) );
double b1 = CubicInterpolation( relativeX, qBlue(p01), qBlue(p11), qBlue(p21), qBlue(p31) );
double b2 = CubicInterpolation( relativeX, qBlue(p02), qBlue(p12), qBlue(p22), qBlue(p32) );
double b3 = CubicInterpolation( relativeX, qBlue(p03), qBlue(p13), qBlue(p23), qBlue(p33) );
int b = qMax(0.0, qMin(255.0, CubicInterpolation(relativeY, b0, b1, b2, b3)));
image.setPixel(i, j, qRgb(r, g, b));
}
}
}
QPixmap pixmap;
pixmap.convertFromImage(image);
pixmapItem_2->setPixmap(pixmap);
scene_2->setSceneRect(QRectF(pixmap.rect()));
calcHist(pixmap, hist_2, maxLevel_2);
drawHist(pixmapItem_4, hist_2, maxLevel_2);
}
void MainWindow::on_actionPiecewise_linear_triggered()
{
QPixmap pixmap = pixmapItem->pixmap().copy();
QImage image = pixmap.toImage();
int width = image.width();
int height = image.height();
if (width == 0 || height == 0)
{
ui->statusBar->showMessage( tr("Error. Image bad size"), 3000 );
return;
}
DialogPiecewiseLinear dialog;
dialog.setText(pieceWiseLinearText);
if (dialog.exec() == QDialog::Rejected)
return;
std::vector<double> nums = dialog.getNums();
pieceWiseLinearText = dialog.getString();
bool normalize = dialog.isNormalize();
std::vector<double> csR(nums.size() / 4);
std::vector<double> csG(nums.size() / 4);
std::vector<double> csB(nums.size() / 4);
if (normalize)
{
int maxR = -1;
int maxG = -1;
int maxB = -1;
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
QRgb oldColor = image.pixel(x, y);
int red = qRed(oldColor);
int green = qGreen(oldColor);
int blue = qBlue(oldColor);
if (red > maxR)
maxR = red;
if (green > maxG)
maxG = green;
if (blue > maxB)
maxB = blue;
}
for (unsigned int i = 0; i < nums.size(); i += 4)
{
csR[i/4] = 255 / (nums[i] * maxR + nums[i+1]);
csG[i/4] = 255 / (nums[i] * maxG + nums[i+1]);
csB[i/4] = 255 / (nums[i] * maxB + nums[i+1]);
}
}
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
QRgb oldColor = image.pixel(x, y);
int red = qRed(oldColor);
int green = qGreen(oldColor);
int blue = qBlue(oldColor);
double cR = 1.0;
double cG = 1.0;
double cB = 1.0;
for (unsigned int i = 0; i < nums.size(); i += 4)
{
double k = nums[i];
double b = nums[i+1];
int left = qFloor(nums[i+2]);
int right = qFloor(nums[i+3]);
if (left <= red && red <= right)
{
if (normalize)
cR = csR[i/4];
red = cR * (k * red + b);
if (red < 0)
red = 0;
if (red > 255)
red = 255;
}
if (left <= green && green <= right)
{
if (normalize)
cG = csG[i/4];
green = cG * (k * green + b);
if (green < 0)
green = 0;
if (green > 255)
green = 255;
}
if (left <= blue && blue <= right)
{
if (normalize)
cB = csB[i/4];
blue = cB * (k * blue + b);
if (blue < 0)
blue = 0;
if (blue > 255)
blue = 255;
}
}
image.setPixel(x, y, qRgb(red, green, blue));
}
pixmap.convertFromImage(image);
pixmapItem_2->setPixmap(pixmap);
scene_2->setSceneRect(QRectF(pixmap.rect()));
calcHist(pixmap, hist_2, maxLevel_2);
drawHist(pixmapItem_4, hist_2, maxLevel_2);
}
AppTemplate::AppTemplate(const Mat* frame_set, const Rect iniWin,int ID)
:ID(ID)//bgr,hsv,lab
{
//get roi out of frame set
Rect body_win=scaleWin(iniWin,1/TRACKING_TO_BODYSIZE_RATIO);
Rect roi_win(body_win.x-body_win.width,body_win.y-body_win.width,3*body_win.width,2*body_win.width+body_win.height);
body_win= body_win&Rect(0,0,frame_set[0].cols,frame_set[0].rows);
roi_win=roi_win&Rect(0,0,frame_set[0].cols,frame_set[0].rows);
Mat roi_set[]={Mat(frame_set[0],roi_win),Mat(frame_set[1],roi_win),Mat(frame_set[2],roi_win)};
Rect iniWin_roi=iniWin-Point(roi_win.x,roi_win.y);
//scores for each channel
list<ChannelScore> channel_score;
Mat mask_roi(roi_set[0].rows,roi_set[0].cols,CV_8UC1,Scalar(0));
rectangle(mask_roi,iniWin_roi,Scalar(255),-1);
Mat inv_mask_roi(roi_set[0].rows,roi_set[0].cols,CV_8UC1,Scalar(255));
rectangle(inv_mask_roi,body_win-Point(roi_win.x,roi_win.y),Scalar(0),-1);
//calculate score for each channel
Mat temp_hist;
Mat temp_bp;
int hist_size[]={BIN_NUMBER};
for (int i=0;i<9;i++)
{
float range1[]={0,255};
if (i==3)
{
range1[1]=179;
}
const float* hist_range[]={range1};
calcHist(roi_set,3,&i,inv_mask_roi,temp_hist,1,hist_size,hist_range);
normalize(temp_hist,temp_hist,255,0.0,NORM_L1);//scale to 255 for display
calcBackProject(roi_set,3,&i,temp_hist,temp_bp,hist_range);
int c[]={0};
int hs[]={BIN_NUMBER};
float hr[]={0,255};
const float* hrr[]={hr};
Mat hist_fore;
Mat hist_back;
calcHist(&temp_bp,1,c,mask_roi,hist_fore,1,hs,hrr);
calcHist(&temp_bp,1,c,inv_mask_roi,hist_back,1,hs,hrr);
normalize(hist_fore,hist_fore,1.0,0.0,NORM_L1);
normalize(hist_back,hist_back,1.0,0.0,NORM_L1);
//deal with gray image to get rid of #IND
double score=getVR(hist_back,hist_fore);
score=score==score ? score:0;
channel_score.push_back(ChannelScore(i,score));
}
//choose the 2 highest scored channels
channel_score.sort(compareChannel);
channels[0]=channel_score.back().idx;
channel_score.pop_back();
channels[1]=channel_score.back().idx;
//using 2 best channel to calculate histogram
for (int i=0;i<2;++i)
{
_hRang[i][0]=0;
if (channels[i]==3)
_hRang[i][1]=179;
else
_hRang[i][1]=255;
hRange[i]=_hRang[i];
}
calcHist(roi_set,3,channels,inv_mask_roi,temp_hist,2,hSize,hRange);
normalize(temp_hist,temp_hist,255,0,NORM_L1);
Mat final_mask;//mask for sampling
calcBackProject(roi_set,3,channels,temp_hist,final_mask,hRange);
threshold(final_mask,final_mask,5,255,CV_THRESH_BINARY_INV);
final_mask=min(final_mask,mask_roi);
//choose the best two feature space for foreground****************
Mat hist_fore,hist_back;
channel_score.clear();
double sum_score=0;
for (int i=0;i<9;i++)
{
float range1[]={0,255};
if (i==3)
{
range1[1]=179;
}
const float* hist_range[]={range1};
Mat temp_hist_neg;
calcHist(roi_set,3,&i,final_mask,temp_hist,1,hist_size,hist_range);
normalize(temp_hist,temp_hist,255,0,NORM_L1);
calcHist(roi_set,3,&i,inv_mask_roi,temp_hist_neg,1,hist_size,hist_range);
normalize(temp_hist_neg,temp_hist_neg,255,0,NORM_L1);
log(temp_hist,temp_hist);
log(temp_hist_neg,temp_hist_neg);
temp_hist=temp_hist-temp_hist_neg;
threshold(temp_hist,temp_hist,0,255,CV_THRESH_TOZERO);
normalize(temp_hist,temp_hist,255,0.0,NORM_L1);//scale to 255 for display
calcBackProject(roi_set,3,&i,temp_hist,temp_bp,hist_range);
int c[]={0};
int hs[]={BIN_NUMBER};
float hr[]={0,255};
const float* hrr[]={hr};
calcHist(&temp_bp,1,c,final_mask,hist_fore,1,hs,hrr);
calcHist(&temp_bp,1,c,inv_mask_roi,hist_back,1,hs,hrr);
normalize(hist_fore,hist_fore,1.0,0.0,NORM_L1);
normalize(hist_back,hist_back,1.0,0.0,NORM_L1);
double score=getVR(hist_back,hist_fore);
score=score==score ? score:0;
channel_score.push_back(ChannelScore(i,score));
sum_score+=exp(score);
}
channel_score.sort(compareChannel);
channels[0]=channel_score.back().idx;
channel_score.pop_back();
channels[1]=channel_score.back().idx;
for (int i=0;i<2;++i)
{
_hRang[i][0]=0;
if (channels[i]==3)
_hRang[i][1]=179;
else
_hRang[i][1]=255;
hRange[i]=_hRang[i];
}
calcHist(roi_set,3,channels,final_mask,hist,2,hSize,hRange);///////////////////
normalize(hist,hist,255,0,NORM_L1);
//recover the shift_vector
Mat backPro;
calcBackProject(roi_set,3,channels,hist,backPro,hRange);
iniWin_roi=iniWin-Point(roi_win.x,roi_win.y);
Point2f origin_point_roi((float)(iniWin_roi.x+0.5*iniWin_roi.width),(float)(iniWin_roi.y+0.5*iniWin_roi.height));
meanShift(backPro,iniWin_roi,TermCriteria( CV_TERMCRIT_EPS | CV_TERMCRIT_ITER, 10, 1 ));
Point2f shift_point_roi((float)(iniWin_roi.x+0.5*iniWin_roi.width),(float)(iniWin_roi.y+0.5*iniWin_roi.height));
shift_vector=(shift_point_roi-origin_point_roi)*(1/(float)iniWin.width);
}
int ThreshHolder::Yen(const Mat &image, bool ignoreBlack, bool ignoreWhite)
{
Mat workingImage = image.clone();
/// Establish the number of bins
int histSize = 256;
/// Set the ranges ( for B,G,R) )
float range[] = {0, 256};
const float *histRange = {range};
Mat data;
calcHist(&workingImage, 1, 0, Mat(), data, 1, &histSize, &histRange);
//Ignore full Black and White
if (ignoreBlack)
{
data.at<float>(0) = 0.0f;
}
if (ignoreWhite)
{
data.at<float>(255) = 0.0f;
}
int threshold;
int ih, it;
float crit;
float max_crit;
float norm_histo[histSize]; /* normalized histogram */
float P1[histSize]; /* cumulative normalized histogram */
float P1_sq[histSize];
float P2_sq[histSize];
int total = 0;
for (ih = 0; ih < histSize; ih++)
{
total += data.at<float>(ih);
}
for (ih = 0; ih < histSize; ih++)
{
norm_histo[ih] = data.at<float>(ih) / total;
}
P1[0] = norm_histo[0];
for (ih = 1; ih < histSize; ih++)
{
P1[ih] = P1[ih - 1] + norm_histo[ih];
}
P1_sq[0] = norm_histo[0] * norm_histo[0];
for (ih = 1; ih < histSize; ih++)
{
P1_sq[ih] = P1_sq[ih - 1] + norm_histo[ih] * norm_histo[ih];
}
P2_sq[histSize - 1] = 0.0;
for (ih = histSize - 2; ih >= 0; ih--)
{
P2_sq[ih] = P2_sq[ih + 1] + norm_histo[ih + 1] * norm_histo[ih + 1];
}
/* Find the threshold that maximizes the criterion */
threshold = -1;
max_crit = INT_MIN;
for (it = 0; it < histSize; it++)
{
crit = -1.0f * ((P1_sq[it] * P2_sq[it]) > 0.0f ? log(P1_sq[it] * P2_sq[it]) : 0.0f) +
2 * ((P1[it] * (1.0f - P1[it])) > 0.0f ? log(P1[it] * (1.0f - P1[it])) : 0.0f);
if (crit > max_crit)
{
max_crit = crit;
threshold = it;
}
}
return threshold;
}
/*
* objective : get the gray level map of the input image and rescale it to the range [0-255]
*/
static void rescaleGrayLevelMat(const cv::Mat &inputMat, cv::Mat &outputMat, const float histogramClippingLimit)
{
// adjust output matrix wrt the input size but single channel
std::cout<<"Input image rescaling with histogram edges cutting (in order to eliminate bad pixels created during the HDR image creation) :"<<std::endl;
//std::cout<<"=> image size (h,w,channels) = "<<inputMat.size().height<<", "<<inputMat.size().width<<", "<<inputMat.channels()<<std::endl;
//std::cout<<"=> pixel coding (nbchannel, bytes per channel) = "<<inputMat.elemSize()/inputMat.elemSize1()<<", "<<inputMat.elemSize1()<<std::endl;
// rescale between 0-255, keeping floating point values
cv::normalize(inputMat, outputMat, 0.0, 255.0, cv::NORM_MINMAX);
// extract a 8bit image that will be used for histogram edge cut
cv::Mat intGrayImage;
if (inputMat.channels()==1)
{
outputMat.convertTo(intGrayImage, CV_8U);
}else
{
cv::Mat rgbIntImg;
outputMat.convertTo(rgbIntImg, CV_8UC3);
cv::cvtColor(rgbIntImg, intGrayImage, cv::COLOR_BGR2GRAY);
}
// get histogram density probability in order to cut values under above edges limits (here 5-95%)... usefull for HDR pixel errors cancellation
cv::Mat dst, hist;
int histSize = 256;
calcHist(&intGrayImage, 1, 0, cv::Mat(), hist, 1, &histSize, 0);
cv::Mat normalizedHist;
normalize(hist, normalizedHist, 1, 0, cv::NORM_L1, CV_32F); // normalize histogram so that its sum equals 1
double min_val, max_val;
minMaxLoc(normalizedHist, &min_val, &max_val);
//std::cout<<"Hist max,min = "<<max_val<<", "<<min_val<<std::endl;
// compute density probability
cv::Mat denseProb=cv::Mat::zeros(normalizedHist.size(), CV_32F);
denseProb.at<float>(0)=normalizedHist.at<float>(0);
int histLowerLimit=0, histUpperLimit=0;
for (int i=1;i<normalizedHist.size().height;++i)
{
denseProb.at<float>(i)=denseProb.at<float>(i-1)+normalizedHist.at<float>(i);
//std::cout<<normalizedHist.at<float>(i)<<", "<<denseProb.at<float>(i)<<std::endl;
if ( denseProb.at<float>(i)<histogramClippingLimit)
histLowerLimit=i;
if ( denseProb.at<float>(i)<1-histogramClippingLimit)
histUpperLimit=i;
}
// deduce min and max admitted gray levels
float minInputValue = (float)histLowerLimit/histSize*255;
float maxInputValue = (float)histUpperLimit/histSize*255;
std::cout<<"=> Histogram limits "
<<"\n\t"<<histogramClippingLimit*100<<"% index = "<<histLowerLimit<<" => normalizedHist value = "<<denseProb.at<float>(histLowerLimit)<<" => input gray level = "<<minInputValue
<<"\n\t"<<(1-histogramClippingLimit)*100<<"% index = "<<histUpperLimit<<" => normalizedHist value = "<<denseProb.at<float>(histUpperLimit)<<" => input gray level = "<<maxInputValue
<<std::endl;
//drawPlot(denseProb, "input histogram density probability", histLowerLimit, histUpperLimit);
drawPlot(normalizedHist, "input histogram", histLowerLimit, histUpperLimit);
// rescale image range [minInputValue-maxInputValue] to [0-255]
outputMat-=minInputValue;
outputMat*=255.0/(maxInputValue-minInputValue);
// cut original histogram and back project to original image
cv::threshold( outputMat, outputMat, 255.0, 255.0, 2 ); //THRESH_TRUNC, clips values above 255
cv::threshold( outputMat, outputMat, 0.0, 0.0, 3 ); //THRESH_TOZERO, clips values under 0
}
void MainWindow::on_actionBrightness_quantization_triggered()
{
QPixmap pixmap = pixmapItem->pixmap().copy();
QImage image = pixmap.toImage();
int width = image.width();
int height = image.height();
if (width == 0 || height == 0)
{
ui->statusBar->showMessage( tr("Error. Image bad size"), 3000 );
return;
}
std::vector<int> grays(width * height);
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
QRgb oldColor = image.pixel(x, y);
int gray = qPow(
0.2126 * qPow(qRed(oldColor), 2.2) +
0.7152 * qPow(qGreen(oldColor), 2.2) +
0.0722 * qPow(qBlue(oldColor), 2.2),
1/2.2
);
grays[x + y * width] = gray;
}
std::vector<unsigned int> Rs(256, 0);
std::vector<unsigned int> Gs(256, 0);
std::vector<unsigned int> Bs(256, 0);
std::vector<int> hist(256, 0);
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
int num = grays[x + y * width];
Rs[num] += qRed( image.pixel(x, y) );
Gs[num] += qGreen( image.pixel(x, y) );
Bs[num] += qBlue( image.pixel(x, y) );
++hist[num];
}
int quantsCountMaximum = 0;
std::map<int, QRgb> colors;
for (int i = 0; i < 256; ++i)
{
if (hist[i] == 0)
continue;
Rs[i] /= hist[i];
Gs[i] /= hist[i];
Bs[i] /= hist[i];
colors[i] = qRgb(Rs[i], Gs[i], Bs[i]);
++quantsCountMaximum;
}
DialogQuantization dialog;
dialog.setQuantCountMaximum(quantsCountMaximum);
if (dialog.exec() == QDialog::Rejected)
return;
int quantsCount = dialog.quantsCount();
double shift = 256 / quantsCount;
double cur = 0.0;
double next = 0.0;
for (int i = 0; i < quantsCount; ++i)
{
next += shift;
int c = qFloor(cur);
int n = qFloor(next);
int minC = 256;
for (std::map<int, QRgb>::iterator it = colors.begin(); it != colors.end(); ++it)
if (c <= (it->first) && (it->first) < n)
if (it->first < minC)
minC = it->first;
QRgb newColor = colors[minC];
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
int num = grays[x + y * width];
if (c <= num && num < n)
image.setPixel(x, y, newColor);
else
continue;
}
cur = next;
}
pixmap.convertFromImage(image);
pixmapItem_2->setPixmap(pixmap);
scene_2->setSceneRect(QRectF(pixmap.rect()));
//ui->graphicsView_2->fitInView(scene_2->itemsBoundingRect(), Qt::KeepAspectRatio);
calcHist(pixmap, hist_2, maxLevel_2);
drawHist(pixmapItem_4, hist_2, maxLevel_2);
}
//-----------------------------------------------------------------------------------------------------
void FrameAnalyzerHistogram::analyze(Mat &input, Mat &output) {
lastFrame=currentFrame;
currentFrame=input;
frameList.append(input);
std::cout << frameList.length() << std::endl;
/// ----------------------------------------------------------------------
vector<Mat> bgr_planes; /// Separate the image in 3 places ( B, G and R )
split(input, bgr_planes);
// Установка количества бинов:
int histSize = 256;
// Установка граничных значений ( for B,G,R) )
float range[] = { 0, 256 };
const float* histRange = { range };
bool uniform = true;
bool accumulate = false;
Mat b_hist, g_hist, r_hist;
// Вычислить гистограммы:
calcHist(&bgr_planes[0], 1, 0, Mat(), b_hist, 1, &histSize, &histRange,
uniform, accumulate);
calcHist(&bgr_planes[1], 1, 0, Mat(), g_hist, 1, &histSize, &histRange,
uniform, accumulate);
calcHist(&bgr_planes[2], 1, 0, Mat(), r_hist, 1, &histSize, &histRange,
uniform, accumulate);
// Отрисовать гистограммы для B, G и R
int hist_w = 640;
int hist_h = 480;
int bin_w = cvRound((double) hist_w / histSize);
Mat histImage(hist_h, hist_w, CV_8UC3, Scalar(0, 0, 0));
// Нормализация результата к [ 0, histImage.rows ]
normalize(b_hist, b_hist, 0, histImage.rows, NORM_MINMAX, -1, Mat());
normalize(g_hist, g_hist, 0, histImage.rows, NORM_MINMAX, -1, Mat());
normalize(r_hist, r_hist, 0, histImage.rows, NORM_MINMAX, -1, Mat());
// Отрисовать для каждого канала
for (int i = 1; i < histSize; i++) {
line(histImage,
Point(bin_w * (i - 1),
hist_h - cvRound(b_hist.at<float>(i - 1))),
Point(bin_w * (i), hist_h - cvRound(b_hist.at<float>(i))),
Scalar(255, 0, 0), 2, 8, 0);
line(histImage,
Point(bin_w * (i - 1),
hist_h - cvRound(g_hist.at<float>(i - 1))),
Point(bin_w * (i), hist_h - cvRound(g_hist.at<float>(i))),
Scalar(0, 255, 0), 2, 8, 0);
line(histImage,
Point(bin_w * (i - 1),
hist_h - cvRound(r_hist.at<float>(i - 1))),
Point(bin_w * (i), hist_h - cvRound(r_hist.at<float>(i))),
Scalar(0, 0, 255), 2, 8, 0);
}
output = histImage;
/*
/// Display
namedWindow("calcHist Demo", CV_WINDOW_AUTOSIZE);
imshow("calcHist Demo", histImage);
*/
}
void MainWindow::on_actionGray_world_triggered()
{
QPixmap pixmap = pixmapItem->pixmap().copy();
QImage image = pixmap.toImage();
int width = image.width();
int height = image.height();
if (width == 0 || height == 0)
{
ui->statusBar->showMessage( tr("Error. Image bad size"), 3000 );
return;
}
double avgRed = 0.0;
double avgGreen = 0.0;
double avgBlue = 0.0;
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
QRgb oldColor = image.pixel(x, y);
avgRed += qRed(oldColor);
avgGreen += qGreen(oldColor);
avgBlue += qBlue(oldColor);
}
int length = width * height;
avgRed /= length;
avgGreen /= length;
avgBlue /= length;
double avg = (avgRed + avgGreen + avgBlue) / 3;
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
QRgb oldColor = image.pixel(x, y);
double red = qRed(oldColor) * avg / avgRed;
double green = qGreen(oldColor) * avg / avgGreen;
double blue = qBlue(oldColor) * avg / avgBlue;
if (red < 0)
red = 0;
if (red > 255)
red = 255;
if (green < 0)
green = 0;
if (green > 255)
green = 255;
if (blue < 0)
blue = 0;
if (blue > 255)
blue = 255;
image.setPixel(x, y, qRgb(red, green, blue));
}
pixmap.convertFromImage(image);
pixmapItem_2->setPixmap(pixmap);
scene_2->setSceneRect(QRectF(pixmap.rect()));
calcHist(pixmap, hist_2, maxLevel_2);
drawHist(pixmapItem_4, hist_2, maxLevel_2);
}
void showHistogram(Mat im,string str)
{
im.convertTo(im, CV_8U);
cout << "th1=" <<TH1<< endl;
string savePath;
/// 设定bin数目
int histSize = 256-TH1;
/// 设定取值范围 ( R,G,B) )
float range[] = { TH1, 255 };
const float* histRange = { range };
bool uniform = true;
bool accumulate = true;
Mat r_hist;
/// 计算直方图:
calcHist(&im, 1, 0, Mat(), r_hist, 1, &histSize, &histRange, uniform, true);
savePath = "./output/histogram_" + str + ".xls";
outXls(savePath,r_hist,"float" );
Mat accumulate_hist = Mat::zeros(r_hist.rows, 1, CV_32F);
// 创建直方图画布
int hist_w = 400; int hist_h = 400;
int bin_w = cvRound((double)hist_w / histSize);
Mat histImage(hist_w, hist_h, CV_8UC3, Scalar(0, 0, 0));
//将负的直方图扩展进来
//accumulate histogram
for (int m = 0; m < r_hist.rows;m++)
{
accumulate_hist.at<float>(m, 0) = sum(r_hist,m);
}
outXls("./output/accuxls.xls", accumulate_hist, "float");
/// 将直方图归一化到范围 [ 0, histImage.rows ],[0,400]
normalize(r_hist, r_hist, 0, histImage.rows, NORM_MINMAX, -1, Mat());
//normalize(accumulate_hist, accumulate_hist, 0, histImage.rows, NORM_MINMAX, -1, Mat());
/// 在直方图画布上画出直方图
for (int i = 1; i < histSize; i++)
{
/*Point up(bin_w*(i - 1), hist_h - cvRound(r_hist.at<float>(i - 1)));
Point bottom(bin_w*(i - 1), hist_h);
line(histImage, bottom, up, Scalar(0, 0, 255), 2, 8, 0);*/
/*line(histImage, Point(bin_w*(i - 1), hist_h - cvRound(accumulate_hist.at<float>(i - 1))),
Point(bin_w*(i), hist_h - cvRound(accumulate_hist.at<float>(i))),
Scalar(0, 0, 255), 2, 8, 0);*/
line(histImage, Point(bin_w*(i - 1), hist_h - cvRound(r_hist.at<float>(i - 1))),
Point(bin_w*(i), hist_h - cvRound(r_hist.at<float>(i))),
Scalar(0, 0, 255), 2, 8, 0);
}
/// 显示直方图
imshow(str, histImage);
}
void MainWindow::on_actionLinear_triggered()
{
QPixmap pixmap = pixmapItem->pixmap().copy();
QImage image = pixmap.toImage();
int width = image.width();
int height = image.height();
if (width == 0 || height == 0)
{
ui->statusBar->showMessage( tr("Error. Image bad size"), 3000 );
return;
}
int minR = 256;
int maxR = -1;
int minG = 256;
int maxG = -1;
int minB = 256;
int maxB = -1;
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
QRgb oldColor = image.pixel(x, y);
int red = qRed(oldColor);
int green = qGreen(oldColor);
int blue = qBlue(oldColor);
if (red < minR)
minR = red;
if (red > maxR)
maxR = red;
if (green < minG)
minG = green;
if (green > maxG)
maxG = green;
if (blue < minB)
minB = blue;
if (blue > maxB)
maxB = blue;
}
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
QRgb oldColor = image.pixel(x, y);
int red = ( qRed(oldColor) - minR) * 255 / (maxR - minR);
int green = ( qGreen(oldColor) - minG) * 255 / (maxG - minG);
int blue = ( qBlue(oldColor) - minB) * 255 / (maxB - minB);
if (red < 0)
red = 0;
if (red > 255)
red = 255;
if (green < 0)
green = 0;
if (green > 255)
green = 255;
if (blue < 0)
blue = 0;
if (blue > 255)
blue = 255;
image.setPixel(x, y, qRgb(red, green, blue));
}
pixmap.convertFromImage(image);
pixmapItem_2->setPixmap(pixmap);
scene_2->setSceneRect(QRectF(pixmap.rect()));
calcHist(pixmap, hist_2, maxLevel_2);
drawHist(pixmapItem_4, hist_2, maxLevel_2);
}
void HistogramOpenCV::liczHistogram(){
calcHist(&grayFrame,1,channel,Mat(),hist,
1,histSize,ranges);
minMaxLoc(hist,&minValue,&maxValue,&indexMin,&indexMax);
scale=(double)heightHistImage/maxValue;
}
void MainWindow::on_actionGamma_correction_triggered()
{
QPixmap pixmap = pixmapItem->pixmap().copy();
QImage image = pixmap.toImage();
int width = image.width();
int height = image.height();
if (width == 0 || height == 0)
{
ui->statusBar->showMessage( tr("Error. Image bad size"), 3000 );
return;
}
DialogGammaCorrection dialog;
if (dialog.exec() == QDialog::Rejected)
return;
int maxR = -1;
int maxG = -1;
int maxB = -1;
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
QRgb oldColor = image.pixel(x, y);
int red = qRed(oldColor);
int green = qGreen(oldColor);
int blue = qBlue(oldColor);
if (red > maxR)
maxR = red;
if (green > maxG)
maxG = green;
if (blue > maxB)
maxB = blue;
}
double gamma = dialog.getGamma();
double cR = 255 / qPow(maxR, gamma);
double cG = 255 / qPow(maxG, gamma);
double cB = 255 / qPow(maxB, gamma);
for (int y = 0; y < height; ++y)
for (int x = 0; x < width; ++x)
{
QRgb oldColor = image.pixel(x, y);
int red = cR * qPow(qRed(oldColor), gamma);
int green = cG * qPow(qGreen(oldColor), gamma);
int blue = cB * qPow(qBlue(oldColor), gamma);
if (red < 0)
red = 0;
if (red > 255)
red = 255;
if (green < 0)
green = 0;
if (green > 255)
green = 255;
if (blue < 0)
blue = 0;
if (blue > 255)
blue = 255;
image.setPixel(x, y, qRgb(red, green, blue));
}
pixmap.convertFromImage(image);
pixmapItem_2->setPixmap(pixmap);
scene_2->setSceneRect(QRectF(pixmap.rect()));
calcHist(pixmap, hist_2, maxLevel_2);
drawHist(pixmapItem_4, hist_2, maxLevel_2);
}
// main function in class BrightnessGroup
// analyze and classify images
void BrightnessGroup::run(){
int i;
// get the number of clusters from user to set the number of group
cout << "How many clusters? ";
cin >> numcluster; cout << endl;
// make the folder to save the result
makebrightnessfolder( numcluster );
// set the size of brightness array to the number of images
brightness = (float*)malloc(sizeof(float)*num);
// for each image,
for( i=0; i<num; i++){
Mat image, hsv_image;
image = images[i];
// extract color element of the image
// if the images doesn't have 3 channels, it's classified to '-1'
if (image.channels() == 3){
// change the mode of image from RGB to HSV
cvtColor(image, hsv_image, CV_BGR2HSV);
// Separate the image in 3 places ( H, S, V )
vector<Mat> hsv_planes;
split( hsv_image, hsv_planes );
// make histogram with brightness element ('v' in hsv means 'value')
int vHistSize = 100;
float vRange[] = {0, 100};
const float* vHistRange = { vRange };
Mat v_hist;
calcHist( &hsv_planes[0], 1, 0, Mat(), v_hist, 1, &vHistSize, &vHistRange, true, false);
int vHist_w = 300; int vHist_h = 400;
int vbin_w = cvRound( (double) vHist_w/vHistSize);
Mat vHistImage( vHist_h, vHist_w, CV_8UC3, Scalar( 0, 0, 0) );
normalize(v_hist, v_hist, 0, vHistImage.rows, NORM_MINMAX, -1, Mat() );
// with histogram of brightness, get the average of the brightness
brightness[i] = avgBrightness(v_hist, vHistSize);
cout << "The average of brightness is " << brightness[i] << endl;
}else{
brightness[i] = -1;
}
cout << "next, go to other picture..." << endl;
}
// with the average of brightness data,
// let the image get its own group by k means clustering
k_means();
// with the clusters array result, classify and save images in appropriate folder
if( flag == IS_FROM_FILES ){
int i=0;
string filename;
// open "filenames.txt" and get the name of file
ifstream file;
file.open("filenames.txt");
// save the images in appropriate folder which is the clusters array result
while(!file.eof() && i<num ){
getline(file, filename);
char newfile[FILE_NAME_MAX+20] = "./brightness_result/";
strcat(newfile, intToString(clusters[i]).c_str());
strcat(newfile, "/");
strcat(newfile, filename.c_str());
cout << "new file adress : " << newfile << endl;
imwrite(newfile, images[i]);
i++;
}
}else if( flag == IS_FROM_URLS ){
int i;
// make the file name to save. It counts from 0 in increasing order
// and save the images in appropriate folder which is the color array
const char file[10] = "photo_";
for( i=0; i<num; i++){
char newfile[FILE_NAME_MAX+20] = "./brightness_result/";
strcat(newfile, intToString(clusters[i]).c_str());
strcat(newfile, "/");
strcat(newfile, file);
if( i < 10 ){
strcat(newfile, "00");
strcat(newfile, intToString(i).c_str());
}else if ( i >= 10 && i < 100 ){
strcat(newfile, "0");
strcat(newfile, intToString(i).c_str());
}else if ( i >= 100 && i < 1000 ){
strcat(newfile, intToString(i).c_str());
}
cout << newfile << endl;
strcat(newfile, ".jpg");
imwrite(newfile, images[i]);
}
}
cout << "brightness grouping finished" << endl;
}
int Judgement::JudgementYON(Mat &image)
{
int success = 0;
MatND dstHist;
Mat histoImg = image.clone();
calcHist(&histoImg, 1, &channels, Mat(), dstHist, 1, &size, ranges);
Mat dstImg(256, 256, CV_8U, Scalar(0));//画直方图
double minValue = 0;
double maxValue = 0;
Point maxloc;
minMaxLoc(dstHist, &minValue, &maxValue, NULL, &maxloc);
//cout << " " << n << "." << m << " " << maxValue << endl;
int hpt = saturate_cast<int>(0.9 * 256);
vector<int> Boundnum;
for (int j = 0; j < 256; j++)
{
float binValue = dstHist.at<float>(j);
int realValue = saturate_cast<int>(binValue * hpt / maxValue);
if (realValue != 0)
{
rectangle(dstImg, Point(j, 255), Point(j, 256 - realValue), Scalar(255));
Boundnum.push_back(j);
}
}
int maxdata = *max_element(Boundnum.begin(), Boundnum.end());
int mindata = *min_element(Boundnum.begin(), Boundnum.end());//寻找直方图动态范围
Rect recttemp;
recttemp.x = maxloc.x;
recttemp.y = maxloc.y - int((maxdata - mindata)*0.15);
recttemp.width = 1;
recttemp.height = int((maxdata - mindata)*0.3);
rectangle(dstHist, recttemp, Scalar(0), -1);
minMaxLoc(dstHist, &minValue, &maxValue, NULL, &maxloc);
int anoThres = maxloc.y;//寻找次峰值
Scalar avgnum;
Mat StdDevImg;
meanStdDev(histoImg, avgnum, StdDevImg);
double Stdnum = StdDevImg.at<double>(Point(0, 0));
int ThreStep = maxdata - mindata;
int StepNum = 30;
int OrStep = mindata + int(ThreStep / 10);
int Dstep = int(ThreStep / 30.0 + 0.5);
if (Dstep == 0)
{
Dstep = 1;
StepNum = ThreStep;
}
Mat TempImg;
histoImg.copyTo(TempImg);
vector<vector<Point>> contours;
vector<Vec4i> hierarchy;
Point pointSN, maxPoint = Point(0, 0);
int Marknumone = 0;
int Marknumtwo = 0;
int Marknumthree = 0;
for (int i = 0; i < StepNum; i++)
{
vector<Point> SN;
OrStep = OrStep + Dstep;
threshold(histoImg, TempImg, OrStep, 255, CV_THRESH_BINARY);
/*Mat element = getStructuringElement(MORPH_RECT,Size(2,2));
erode(TempImg, TempImg, cv::Mat());
dilate(TempImg, TempImg, cv::Mat());*/
TempImg = ~TempImg;
/*stringstream strstrone;
strstrone << "水渍动态图" << i << ".jpg";
imwrite(strstrone.str(), TempImg);*/
Mat BoundImg(TempImg.rows, TempImg.cols, CV_8UC1, Scalar(255));
Rect Wrect;
Wrect.x = 1;
Wrect.y = 1;
Wrect.width = BoundImg.cols - 2;
Wrect.height = BoundImg.rows - 2;
rectangle(BoundImg, Wrect, Scalar(0), -1);
Mat PlusImg(TempImg.rows + 2, TempImg.cols + 2, CV_8UC1, Scalar(255));
Mat PlusROI = PlusImg(Rect(1, 1, TempImg.cols, TempImg.rows));
TempImg.copyTo(PlusROI);
Mat ContoursImg = PlusImg.clone();
findContours(ContoursImg, contours, hierarchy, RETR_TREE, CV_CHAIN_APPROX_SIMPLE);
for (size_t j = 0; j < contours.size(); j++)
{
double area = cv::contourArea(contours[j]);
pointSN.x = int(area);
pointSN.y = j;
SN.push_back(pointSN);
}
if (contours.size() != 0)
{
sort(SN.begin(), SN.end(), SortByM2);
maxPoint = SN.back();
if (OrStep > anoThres - 5 && OrStep<anoThres + 20)
Dstep = 1;
else
{
Dstep = int(ThreStep / 30.0 + 0.5);
}
if (Dstep == 0)
Dstep = 1;
int k = maxPoint.y;
Mat MarkImg(TempImg.rows, TempImg.cols, CV_8UC1, Scalar(0));
drawContours(MarkImg, contours, k, Scalar(255), -1);
bitwise_and(BoundImg, MarkImg, MarkImg);
int Mbound = 0;//判断轮廓是否到边界
Mbound = countNonZero(MarkImg);
if (Mbound>0.5*(histoImg.cols))
break;
if (contours[k].size() <= 4)
continue;
int son = hierarchy[k][2];
Point gravitycore = barycenter(contours[k]);//寻找轮廓重心
Rect maxcontours = boundingRect(contours[k]);
int wValue = maxcontours.width / 12;
gravitycore = gravitycore + Point(wValue - 1, wValue - 1);
Mat gravityImg(TempImg.rows + 2 * wValue, TempImg.cols + 2 * wValue, CV_8UC1, Scalar(0));
Mat gravityImgROI = gravityImg(Rect(wValue, wValue, TempImg.cols, TempImg.rows));
TempImg.copyTo(gravityImgROI);
Rect gravityrect = Rect(gravitycore - Point(1, 1), gravitycore + Point(2 * wValue, 2 * wValue) - Point(2, 2));//画出重心周围(2 * wValue)*(2 * wValue)的矩形区域
if (gravityrect.x < 0 || gravityrect.y < 0)
continue;
int avnum = countNonZero(gravityImg(Rect(gravityrect)));
vector<Point> hull;
convexHull(contours[k], hull, false);
double promark = (contourArea(contours[k])) / (contourArea(hull));
if (son >= 0)//判断是否为父轮廓
{
int sonarea = 0;
for (size_t j = 0; j < contours.size(); j++)
{
if (hierarchy[j][3] == k&&contourArea(contours[j])>4.0)
sonarea = sonarea + contourArea(contours[j]);
}
if (50 * sonarea>maxPoint.x)//此处忽略一些偶然出现的中空点
Marknumone++;
}
if (avnum < double(0.5 * gravityrect.width*gravityrect.width))//在重心区域中的白色点的数量是否过半
Marknumtwo++;
if (promark < 0.6)
Marknumthree++;
}
}
if (Marknumone > 2 || Marknumtwo >= 2 || Marknumthree > 3)//缺陷点也可能偶然出现包含
{
/*cout << "该点是水渍2" << endl;*/
}
else
{
/*cout << "该点是缺陷2" << endl;*/
success++;
}
return success;
}
void ModalityColor3DHistogram::update(Image& image, PatchSet* patchSet, Rect bounds) {
Ptr<PatchSet> patches = Ptr<PatchSet>(reliablePatchesFilter.empty() ? patchSet : patchSet->filter(*reliablePatchesFilter));
Rect background_outer = expand(bounds, background_size + background_margin);
Rect background_inner = expand(bounds, background_margin);
MatND new_foreground, new_background;
//tmp_float.convertTo(image.get(colorspace), CV_32F, 1.0/255.0);
Mat arrays[] = {image.get(colorspace)};
Mat mask = image.get_mask();
mask.setTo(0);
int half_size = patches->get_radius() * foreground_size;
// Foreground histogram
for (int i = 0; i < patches->size(); i++) {
Point2f pos = patches->get_position(i);
Rect r;
r.x = CLAMP3( ((int)pos.x - half_size), 0, mask.cols);
r.y = CLAMP3( ((int)pos.y - half_size), 0, mask.rows);
r.width = CLAMP3( ((int)pos.x + half_size), 0, mask.cols) - r.x;
r.height = CLAMP3( ((int)pos.y + half_size), 0, mask.rows) - r.y;
if (r.width < 1 || r.height < 1) { continue; }
mask(r) = 1;
}
calcHist(arrays, 1, channels, mask, new_foreground, 3, histSize, ranges, true, false);
calcHist(arrays, 1, channels, mask, new_foreground, 3, histSize, ranges, true, false);
mask.setTo(0);
/*Point2f* convex_points = new Point2f[patches.size()];
for (int i = 0; i < patches.size(); i++) {
convex_points[i] = patches.get_position(i);
}
fillconvex(mask, convex_points, convex_points.size(), Scalar(1));*/
Rect outer = expand(bounds, background_size + background_margin);
rectangle(mask, outer.tl(), outer.br(), Scalar(1), FILLED);
Rect inner = expand(bounds, background_margin);
rectangle(mask, inner.tl(), inner.br(), Scalar(0), FILLED);
rectangle(mask, background_outer.tl(), background_outer.br(), Scalar(1), FILLED);
rectangle(mask, background_inner.tl(), background_inner.br(), Scalar(0), FILLED);
calcHist(arrays, 1, channels, mask, new_background, 3, histSize, ranges, true, false);
new_background += 1;
// Merging model with new data
float* ofd = (float*) foreground.data;
float* nfd = (float*) new_foreground.data;
float* obd = (float*) background.data;
float* nbd = (float*) new_background.data;
float* md = (float*) model.data;
float apriori = (float)(bounds.width * bounds.height) / (float)(image.width() * image.height()); // TODO: justify factor
int histCount = histSize[0] * histSize[1] * histSize[2];
float nfdSum = 0, nbdSum = 0;
for (int i = 0; i < histCount; i++) {
nfdSum += nfd[i];
nbdSum += nbd[i];
}
float nfdSum2 = 0, nbdSum2 = 0;
if (nfdSum > 0) {
for (int i = 0; i < histCount; i++) {
ofd[i] = foreground_presistence * ofd[i] + (1 - foreground_presistence) * (nfd[i] / nfdSum);
nfdSum2 += ofd[i];
}
} else {
for (int i = 0; i < histCount; i++)
{ nfdSum2 += ofd[i]; }
}
if (nbdSum > 0) {
for (int i = 0; i < histCount; i++) {
obd[i] = background_presistence * obd[i] + (1 - background_presistence) * (nbd[i] / nbdSum);
nbdSum2 += obd[i];
}
} else {
for (int i = 0; i < histCount; i++)
{ nbdSum2 += obd[i]; }
}
for (int i = 0; i < histCount; i++)
{ md[i] = ((apriori * (ofd[i] / nfdSum2)) / (apriori * (ofd[i] / nfdSum2) + (1 - apriori) * (obd[i] / nbdSum2))) * 255; }
has_data = true;
}
int main(int argc, char* argv[])
{
char* filename = argc == 2 ? argv[1] : "test.avi";
VideoCapture capture(filename);
if (!capture.isOpened())
return -1;
namedWindow("Video", CV_WINDOW_AUTOSIZE);
//namedWindow("Hist", CV_WINDOW_AUTOSIZE);
vector<int> vec;
int number = 0;
int width = capture.get(CV_CAP_PROP_FRAME_WIDTH);
int height = capture.get(CV_CAP_PROP_FRAME_HEIGHT);
int wait = 1000 / capture.get(CV_CAP_PROP_FPS);
int temp = width * PERCENT_EDGE;
long int amount_pixels = (width * height) - (2 * temp * height);
cv::Mat mask(height, width, CV_8U, 0.0); // создание маски, дл¤ подсчета гистограммы без учЄта краЄв
rectangle(mask, cv::Point(temp,0), cv::Point(width - temp, height), 1, CV_FILLED);
// ѕараметры гистограммы
int histSize = 256;
float range[] = { 0, 256 };
const float* histRange = { range };
bool uniform = true;
bool accumulate = false;
int hist_w = 512;
int hist_h = 400;
int bin_w = cvRound((double)hist_w / histSize);
while (capture.isOpened())
{
Mat src;
if (!capture.read(src)) break;
imshow("Video", src);
// Ѕудем считать гистогрмму только дл¤ канала R
std::vector<Mat> bgr_planes;
split(src, bgr_planes);
Mat r_hist;
calcHist(&bgr_planes[2], 1, 0, mask, r_hist, 1, &histSize, &histRange, uniform, accumulate);
Mat histImage(hist_h, hist_w, CV_8UC3, Scalar(0, 0, 0));
HistEvidenceAnaliz(&r_hist, histSize, amount_pixels, &vec, number);
// Normalize the result to [ 0, histImage.rows ]
//normalize(r_hist, r_hist, 0, histImage.rows, NORM_MINMAX, -1, Mat());
// Draw Hist
/*for (int i = 1; i < histSize; i++)
{
line(histImage, Point(bin_w*(i - 1), hist_h - cvRound(r_hist.at<float>(i - 1))),
Point(bin_w*(i), hist_h - cvRound(r_hist.at<float>(i))),
Scalar(0, 0, 255), 2, 8, 0);
}*/
//imshow("Hist", histImage);
if (waitKey(wait) >= 0) break;
}
vector<pair<int, int>> linking_frames;
int counter = 0;
int start = 0;
for (vector<int>::iterator it = vec.begin(); it != vec.end(); it++)
{ // рассчЄт мест сшивки, чтобы избежать попадани¤ случайных кадров
if ((it + 1) != vec.end())
{
if (*(it + 1) - *it <= THRESHOLD_GAP_FRAME)
{
if (counter == 0) start = *it;
counter++;
}
else
{
if (counter < THRESHOLD_FRAME_SEQUENCE) counter = 0;
else
{
if ((*it) - start > MIN_LENGTH_SEQUENCE_FRAME) linking_frames.push_back(pair<int, int>(start, *it));
counter = 0;
}
}
}
else if (counter >= THRESHOLD_FRAME_SEQUENCE)
{
if ((*it) - start > MIN_LENGTH_SEQUENCE_FRAME)
linking_frames.push_back(pair<int, int>(start, *it));
}
}
cout << "Linking frames:" << endl;
for (vector<pair<int, int>>::iterator it = linking_frames.begin(); it != linking_frames.end(); it++)
cout << it->first << " - " << it->second << endl;
getchar();
return 0;
}
/*
* objective : get the gray level map of the input image and rescale it to the range [0-255] if rescale0_255=TRUE, simply trunks else
*/
static void rescaleGrayLevelMat(const cv::Mat &inputMat, cv::Mat &outputMat, const float histogramClippingLimit, const bool rescale0_255)
{
// adjust output matrix wrt the input size but single channel
std::cout<<"Input image rescaling with histogram edges cutting (in order to eliminate bad pixels created during the HDR image creation) :"<<std::endl;
//std::cout<<"=> image size (h,w,channels) = "<<inputMat.size().height<<", "<<inputMat.size().width<<", "<<inputMat.channels()<<std::endl;
//std::cout<<"=> pixel coding (nbchannel, bytes per channel) = "<<inputMat.elemSize()/inputMat.elemSize1()<<", "<<inputMat.elemSize1()<<std::endl;
// get min and max values to use afterwards if no 0-255 rescaling is used
double maxInput, minInput, histNormRescalefactor=1.f;
double histNormOffset=0.f;
minMaxLoc(inputMat, &minInput, &maxInput);
histNormRescalefactor=255.f/(maxInput-minInput);
histNormOffset=minInput;
std::cout<<"Hist max,min = "<<maxInput<<", "<<minInput<<" => scale, offset = "<<histNormRescalefactor<<", "<<histNormOffset<<std::endl;
// rescale between 0-255, keeping floating point values
cv::Mat normalisedImage;
cv::normalize(inputMat, normalisedImage, 0.f, 255.f, cv::NORM_MINMAX);
if (rescale0_255)
normalisedImage.copyTo(outputMat);
// extract a 8bit image that will be used for histogram edge cut
cv::Mat intGrayImage;
if (inputMat.channels()==1)
{
normalisedImage.convertTo(intGrayImage, CV_8U);
} else
{
cv::Mat rgbIntImg;
normalisedImage.convertTo(rgbIntImg, CV_8UC3);
cv::cvtColor(rgbIntImg, intGrayImage, cv::COLOR_BGR2GRAY);
}
// get histogram density probability in order to cut values under above edges limits (here 5-95%)... usefull for HDR pixel errors cancellation
cv::Mat dst, hist;
int histSize = 256;
calcHist(&intGrayImage, 1, 0, cv::Mat(), hist, 1, &histSize, 0);
cv::Mat normalizedHist;
normalize(hist, normalizedHist, 1.f, 0.f, cv::NORM_L1, CV_32F); // normalize histogram so that its sum equals 1
// compute density probability
cv::Mat denseProb=cv::Mat::zeros(normalizedHist.size(), CV_32F);
denseProb.at<float>(0)=normalizedHist.at<float>(0);
int histLowerLimit=0, histUpperLimit=0;
for (int i=1; i<normalizedHist.size().height; ++i)
{
denseProb.at<float>(i)=denseProb.at<float>(i-1)+normalizedHist.at<float>(i);
//std::cout<<normalizedHist.at<float>(i)<<", "<<denseProb.at<float>(i)<<std::endl;
if ( denseProb.at<float>(i)<histogramClippingLimit)
histLowerLimit=i;
if ( denseProb.at<float>(i)<1.f-histogramClippingLimit)
histUpperLimit=i;
}
// deduce min and max admitted gray levels
float minInputValue = (float)histLowerLimit/histSize*255.f;
float maxInputValue = (float)histUpperLimit/histSize*255.f;
std::cout<<"=> Histogram limits "
<<"\n\t"<<histogramClippingLimit*100.f<<"% index = "<<histLowerLimit<<" => normalizedHist value = "<<denseProb.at<float>(histLowerLimit)<<" => input gray level = "<<minInputValue
<<"\n\t"<<(1.f-histogramClippingLimit)*100.f<<"% index = "<<histUpperLimit<<" => normalizedHist value = "<<denseProb.at<float>(histUpperLimit)<<" => input gray level = "<<maxInputValue
<<std::endl;
//drawPlot(denseProb, "input histogram density probability", histLowerLimit, histUpperLimit);
drawPlot(normalizedHist, "input histogram", histLowerLimit, histUpperLimit);
if(rescale0_255) // rescale between 0-255 if asked to
{
cv::threshold( outputMat, outputMat, maxInputValue, maxInputValue, 2 ); //THRESH_TRUNC, clips values above maxInputValue
cv::threshold( outputMat, outputMat, minInputValue, minInputValue, 3 ); //THRESH_TOZERO, clips values under minInputValue
// rescale image range [minInputValue-maxInputValue] to [0-255]
outputMat-=minInputValue;
outputMat*=255.f/(maxInputValue-minInputValue);
} else
{
inputMat.copyTo(outputMat);
// update threshold in the initial input image range
maxInputValue=(float)((maxInputValue-255.f)/histNormRescalefactor+maxInput);
minInputValue=(float)(minInputValue/histNormRescalefactor+minInput);
std::cout<<"===> Input Hist clipping values (max,min) = "<<maxInputValue<<", "<<minInputValue<<std::endl;
cv::threshold( outputMat, outputMat, maxInputValue, maxInputValue, 2 ); //THRESH_TRUNC, clips values above maxInputValue
cv::threshold( outputMat, outputMat, minInputValue, minInputValue, 3 ); //
}
}
void CImageAnalysis::OnBnClickedHough()
{
CMainFrame * pwnd = (CMainFrame *)AfxGetMainWnd();
GetDlgItem(IDC_Show);
Mat mat = imread( "F:\\4点定位剪切图.bmp",CV_LOAD_IMAGE_ANYDEPTH|CV_LOAD_IMAGE_ANYCOLOR );
Mat src,src1,src2;
mat.copyTo(src);
medianBlur(src,src1,5);//中值滤波
int threshold1=100;
Mat hist;
int histSize = 255;
float range[] = { 0, 255 } ;
const float* histRange = { range };
bool uniform = true;
bool accumulate = false;
calcHist( &src1, 1, 0, Mat(), hist, 1, &histSize, &histRange, uniform, accumulate );
int hist_w = 400; int hist_h = 400;
int bin_w = cvRound( (double) 3*hist_w/histSize );
Mat histImage( hist_w, hist_h, CV_8UC3, Scalar( 255,255,255) );
normalize(hist, hist, 0, histImage.rows, NORM_MINMAX, -1, Mat() );
for( int i = 1; i < 255; i++ )
{
line( histImage, Point( bin_w*(i-1), hist_h - cvRound(hist.at<float>(i-1)) ) ,
Point( bin_w*(i), hist_h - cvRound(hist.at<float>(i)) ),
Scalar( 0, 0, 0), 2, 8, 0 );
/*line( histImage, Point( bin_w*(i), hist_h - cvRound(hist.at<float>(i)) ) ,
Point( bin_w*(i), hist_h ),
Scalar( 0, 0, 0), 2, 8, 0 );*/
}
namedWindow("calcHist Demo", CV_WINDOW_AUTOSIZE );
imshow("calcHist Demo", histImage );
imwrite("hist.bmp",histImage);
//Histogram();
//m_Show.ShowImage(hist,0);
//threshold(src1,src1,threshold1,255,THRESH_BINARY);//二值图的生成；
//vector<vector<Point> > contours;
//vector<Vec3f> circles;
//findContours(src2,contours,CV_RETR_LIST,CV_CHAIN_APPROX_NONE);
// Apply the Hough Transform to find the circles
/*HoughCircles( src,circles, CV_HOUGH_GRADIENT, 1, 1, 200, 10, 2,1000);
for( size_t i = 0; i < circles.size(); i++ )
{
Point center(cvRound(circles[i][0]), cvRound(circles[i][1]));
int radius = cvRound(circles[i][2]);
// circle center
circle( src, center, 3, Scalar(0,255,0), -1, 8, 0 );
// circle outline
circle( src, center, radius, Scalar(0,0,255), 3, 8, 0 );
}*/
/*pwnd->m_imageprocess.ImageRotate(src1,src2,1.5);
Mat src3=Mat::zeros(src2.rows,src2.cols,src2.type());//src2.cols+10
Mat dst=Mat::zeros(src2.rows,src2.cols,src2.type());
int src2_half_rows=src2.rows/2;
int src1_half_rows=src1.rows/2;
int i,j,k;
uchar *p,*q;
MatIterator_<uchar> begin1,begin2;
begin1=src1.begin<uchar>();
begin2=src2.begin<uchar>();
for(i=src2_half_rows-src1_half_rows;i!=src2_half_rows+src1_half_rows;++i)
{
p=src3.ptr<uchar>(i);
for(j=0;j!=src1.cols;++j)
{
p[j]=*begin1;
++begin1;
}
}
int dx=825,dy=5;//dst中只装载src1 小于（828，0）则向原点移动
for (int i = 0; i < dst.rows; i++)
{
p = dst.ptr<uchar>(i);
for (int j = 0; j < dst.cols; j++)
{
//平移后坐标映射到原图像
int x = j - dx;
int y = i - dy;
//保证映射后的坐标在原图像范围内
if (x >= 0 && y >= 0 && x <src3. cols && y < src3.rows)
p[j] = src3.ptr<uchar>(y)[x];
}
}
for(i=0;i!=src2.rows;++i)
{
q=dst.ptr<uchar>(i);
for(j=0;j!=src2.cols;++j)//src2.cols+10
{
k=q[j]/2+*begin2/2;
q[j]=k;
++begin2;
}
}
//m_Show.ShowImage(src2,0);
//m_Show.ShowImage(dst,0);
//imwrite("F:\\result1.bmp",dst);
threshold(dst,dst,threshold1,255,THRESH_BINARY);//二值图的生成；
vector<vector<Point> > contours;
findContours(dst,contours,CV_RETR_LIST,CV_CHAIN_APPROX_NONE);
//system("pause");
/// 绘出轮廓
Mat gray ;
cvtColor(dst,gray , CV_GRAY2BGR);
for( int i = 0; i<contours.size(); i++ )
{
drawContours( gray, contours, i, Scalar(255,0,0), 2, 8, contours[0], 0, Point() );
}
m_Show.ShowImage(hist,0);*/
}
bool cv::find4QuadCornerSubpix(InputArray _img, InputOutputArray _corners, Size region_size)
{
CV_INSTRUMENT_REGION();
Mat img = _img.getMat(), cornersM = _corners.getMat();
int ncorners = cornersM.checkVector(2, CV_32F);
CV_Assert( ncorners >= 0 );
Point2f* corners = cornersM.ptr<Point2f>();
const int nbins = 256;
float ranges[] = {0, 256};
const float* _ranges = ranges;
Mat hist;
Mat black_comp, white_comp;
for(int i = 0; i < ncorners; i++)
{
int channels = 0;
Rect roi(cvRound(corners[i].x - region_size.width), cvRound(corners[i].y - region_size.height),
region_size.width*2 + 1, region_size.height*2 + 1);
Mat img_roi = img(roi);
calcHist(&img_roi, 1, &channels, Mat(), hist, 1, &nbins, &_ranges);
int black_thresh = 0, white_thresh = 0;
segment_hist_max(hist, black_thresh, white_thresh);
threshold(img, black_comp, black_thresh, 255.0, THRESH_BINARY_INV);
threshold(img, white_comp, white_thresh, 255.0, THRESH_BINARY);
const int erode_count = 1;
erode(black_comp, black_comp, Mat(), Point(-1, -1), erode_count);
erode(white_comp, white_comp, Mat(), Point(-1, -1), erode_count);
std::vector<std::vector<Point> > white_contours, black_contours;
findContours(black_comp, black_contours, RETR_LIST, CHAIN_APPROX_SIMPLE);
findContours(white_comp, white_contours, RETR_LIST, CHAIN_APPROX_SIMPLE);
if(black_contours.size() < 5 || white_contours.size() < 5) continue;
// find two white and black blobs that are close to the input point
std::vector<std::pair<int, float> > white_order, black_order;
orderContours(black_contours, corners[i], black_order);
orderContours(white_contours, corners[i], white_order);
const float max_dist = 10.0f;
if(black_order[0].second > max_dist || black_order[1].second > max_dist ||
white_order[0].second > max_dist || white_order[1].second > max_dist)
{
continue; // there will be no improvement in this corner position
}
const std::vector<Point>* quads[4] = {&black_contours[black_order[0].first], &black_contours[black_order[1].first],
&white_contours[white_order[0].first], &white_contours[white_order[1].first]};
std::vector<Point2f> quads_approx[4];
Point2f quad_corners[4];
for(int k = 0; k < 4; k++)
{
std::vector<Point2f> temp;
for(size_t j = 0; j < quads[k]->size(); j++) temp.push_back((*quads[k])[j]);
approxPolyDP(Mat(temp), quads_approx[k], 0.5, true);
findCorner(quads_approx[k], corners[i], quad_corners[k]);
quad_corners[k] += Point2f(0.5f, 0.5f);
}
// cross two lines
Point2f origin1 = quad_corners[0];
Point2f dir1 = quad_corners[1] - quad_corners[0];
Point2f origin2 = quad_corners[2];
Point2f dir2 = quad_corners[3] - quad_corners[2];
double angle = acos(dir1.dot(dir2)/(norm(dir1)*norm(dir2)));
if(cvIsNaN(angle) || cvIsInf(angle) || angle < 0.5 || angle > CV_PI - 0.5) continue;
findLinesCrossPoint(origin1, dir1, origin2, dir2, corners[i]);
}
return true;
}
void HashAllItems(const Mat& feature, const Mat& proj, HashParam& p)
{
printf("start to build the bucket info ...\n");
int nl = feature.rows;
int nc = feature.cols;
//hash every items
//core:compute value for hash, but the type is continus, float, and not normalised
Mat projectValue;
ProjectAll(p, feature, proj, projectValue);
//change the range(minRange, maxRange) to {0, 1, ..., bucketLength-1}
//hash process
p.hashPoint.create(nl, p.bucketNumber, CV_32SC1);
float mid = p.range /2;
float pi = 3.14159265;
#ifdef HASH_FUNC_ORIGINAL
p.r = (p.bucketLength - 1)/p.range;
#endif
#ifdef HASH_FUNC_SIGMOID
float y1 = 1.0;
float x1 = 0;
int acc = 0, wc = 0;
int bins = p.bucketLength;
float seg = p.range / bins;
int delta = 4;
vector<int> hh = calcHist(projectValue.ptr<float>(0), nl, bins);
vector<int> shh = smooth(hh, bins);
for(int i = 0; i < bins; i ++)
{
//printf("%d", shh[i]);
if(shh[i] < delta)
{
acc += shh[i];
wc ++;
}
else
break;
}
printf("wc: %d, acc: %d, seg: %f\n", wc, acc, seg);
y1 = acc * bins * 1.0/ nl * 2;
x1 = wc * seg - p.range/2;
p.a = p.bucketLength;
p.b = 1.0;
p.c = -log(p.a/y1 - p.b)/x1;
printf("x1: %f, y1: %f, p.c: %f\n", x1, y1, p.c);
#endif
#ifdef HASH_FUNC_ATAN
p.a = (p.bucketLength - 1)/pi;
p.b = 2.0;
p.c = (p.bucketLength-1)/2;
#endif
#ifdef HASH_FUNC_LOG
#endif
FILE* out = fopen("/home/administrator/data.dat", "w");
for(int bucket = 0; bucket < p.bucketNumber; bucket ++)
{
for(int pp = 0; pp < nl; pp ++)
{
float y = projectValue.at<float>(bucket, pp) - p.minRange;
if(bucket == 0)
{
fprintf(out, "%f ", y);
}
#ifdef HASH_FUNC_ORIGINAL
y = y * r;
#endif
//x**3
#ifdef HASH_FUNC_POWER_THREE
printf("using hash function 2\n");
y = 2 * y / p.range - 1;
if(y < 0)
{
y = 0 - pow(0 - y, 1.0/3.0);
}
else
{
y = pow(y, 1.0/3.0);
}
y = (y + 1) * (p.bucketLength - 1) /2.0;
#endif
//sigmoid a/(1 + b * exp(-c*x))
#ifdef HASH_FUNC_SIGMOID
y = y - mid;
y = p.a / (1 + p.b * exp(-p.c * y));
#endif
//atan a*atan(b*x)+c
#ifdef HASH_FUNC_ATAN
y = y - mid;
y = p.a * atan(p.b * y) + p.c;
#endif
//
#ifdef HASH_FUNC_LOG
#endif
int h = (int)(y);
if(h < 0 || h >= p.bucketLength)
{
printf("y: %f, h: %d\n", y, h);
programPause();
}
p.bucketInfo[bucket][h].push_back(pp);
//p.hashPoint.at<int>(pp, bucket) = h;
}
}//end of hash every items
fclose(out);
printf("\nexit projection ...\n");
/*int showPixels = 1;
Mat img = Mat::zeros(nl/levels * 5, showPixels*levels, CV_8UC3);
Scalar color(0, 255, 255);
int showlevels = p.bucketInfo[0].size();
//int showlevels = levels;
for(int i = 0; i < showlevels; i ++)
{
int v = p.bucketInfo[0][i].size();
printf("%d ", v);
//rectangle(img, Point(i*showPixels, 0), Point(i*showPixels, min(v, img.rows-1)), color, CV_FILLED);
}
printf("\n");
namedWindow("bins");
imshow("bins", img);
waitKey(0);*/
programPause();
}
