int get_notes_possitions(const SDoublePlane &input, const SDoublePlane &tmpl,
double threshold, SDoublePlane &output, Type t,
vector<DetectedSymbol> &symbols)
{
// non-maximum suppress size
int sup_w, sup_h;
//shawn calc hamming distance
// get template image
//SDoublePlane template_note = SImageIO::read_png_file("template1.png");
// get distance
SDoublePlane hammdis_note = get_Hamming_distance(input, tmpl);
if (t == NOTEHEAD)
{
write_image("scores4.png", hammdis_note);
}
//write_image("hamming_dist_note.png", hammdis_note);
// print_image_value(hammdis_note);
// cout << plane_max(hammdis_note) / 255 << endl;
// non-maximum suppress
SDoublePlane sup_note = non_maximum_suppress(hammdis_note, threshold*255, tmpl.cols()*0.5, tmpl.rows()-(int)(tmpl.rows()*0.4));
//write_image("sup_hamming_dist_note.png", sup_note);
get_symbols(sup_note, symbols, t, tmpl.cols(), tmpl.rows());
return 0;
}
void set_disparity(int start, int end, vector<SDoublePlane> &D, SDoublePlane &V, vector<vector<SDoublePlane> > &m)
{
//disp_arg *A = (disp_arg*)obj;
double disp_score;
double min_score = INT_MAX;
int label, t=1;
double neighbors_sum;
start = (start < 1)? 1:start;
end = (end < (V.rows()-1))?end:(V.rows()-1);
for (int i = start; i < end-1; i++) {
for (int j = 1; j < D[0].cols() - 1; j++) {
min_score = INT_MAX;
label = DLIMIT;
for (int d = 0; d < DLIMIT; d++) {
//cout << i<<","<<j<<endl;
neighbors_sum = get_messages_from_neighbors(m[d][t], i, j, ALL);
disp_score = D[d][i][j] + neighbors_sum;
if (disp_score < min_score) {
min_score = disp_score;
label = d;
}
}
V[i][j] = label;
}
}
}
// Finding Line Location for Q4. As this was a open ended question, we found the number of lines using this approach.
vector<LineLocation> find_line_location(SDoublePlane &input){
int rows = input.rows();
int cols = input.cols();
vector<LineLocation> allLinesLocVector;
double sum;
int lineCounter = 1;
int j;
for(int i=0;i<rows;i++)
{ sum =0;
for(j=cols - 45;j<cols -40;j++){
sum += input[i][j];
}
if(sum/5 < 130){
LineLocation lineLoc;
lineLoc.row = i;
lineLoc.col = j;
set_line_tags(lineLoc, lineCounter);
lineCounter++;
allLinesLocVector.push_back(lineLoc);
}
}
return allLinesLocVector;
}
// Convolve an image with a separable convolution kernel
//
SDoublePlane convolve_separable(const SDoublePlane &input, const SDoublePlane &row_filter, const SDoublePlane &col_filter)
{
SDoublePlane output(input.rows(), input.cols());
output = convolve_general(input, row_filter);
return convolve_general(output, col_filter);
}
void write_staves_image(const string &filename, const SDoublePlane &img, vector<Line> linesVector){
SDoublePlane output_planes[3];
for (int i = 0; i < 3; i++)
output_planes[i] = img;
int r = img.rows();
int c = img.cols();
int x1, y1, x2, y2;
for (int i = 0; i < linesVector.size(); i++) {
x1 = linesVector[i].x1;
y1 = linesVector[i].y1;
x2 = linesVector[i].x2;
y2 = linesVector[i].y2;
//cout<<"(x1,y1): ("<<x1<<","<<y1<<"), (x2,y2):("<<x2<<","<<y2<<")\n";
overlay_rectangle(output_planes[2], y1, x1, y2, x2, 255, 2);
overlay_rectangle(output_planes[0], y1, x1, y2, x2, 0, 2);
overlay_rectangle(output_planes[1], y1, x1, y2, x2, 0, 2);
}
SImageIO::write_png_file(filename.c_str(), output_planes[0],
output_planes[1], output_planes[2]);
}
// Apply a sobel operator to an image, returns the result
// _gx=true for horizontal gradient, false for vertical gradient
SDoublePlane sobel_gradient_filter(const SDoublePlane &input, bool _gx)
{
SDoublePlane output(input.rows(), input.cols());
SDoublePlane row_filter(1, 3), col_filter(3, 1);
if (_gx)
{
row_filter[0][0] = -1.0;
row_filter[0][1] = 0.0;
row_filter[0][2] = 1.0;
col_filter[0][0] = 1.0/8.0;
col_filter[1][0] = 2.0/8.0;
col_filter[2][0] = 1.0/8.0;
}
else
{
row_filter[0][0] = 1.0/8.0;
row_filter[0][1] = 2.0/8.0;
row_filter[0][2] = 1.0/8.0;
col_filter[0][0] = 1.0;
col_filter[1][0] = 0.0;
col_filter[2][0] = -1.0;
}
SDoublePlane sobel = convolve_separable(input, row_filter, col_filter);
return sobel;
}
SDoublePlane non_maximum_suppress(const SDoublePlane &input, double threshold, int w, int h)
{
//double threshold = 0.84 * 255;
SDoublePlane output(input.rows(), input.cols());
for (int i = 0; i < input.rows(); i++)
{
for (int j = 0; j < input.cols(); j++)
{
if (input[i][j] > threshold &&
is_max_in_neighbour(input, i, j, w, h))
{
if (input[i][j] > 0.85 * 255)
{
output[i][j] = 255;
}
else
{
output[i][j] = (input[i][j] - threshold)/(0.85 - threshold/255);
}
}
else
{
output[i][j] = 0;
}
}
}
return output;
}
SDoublePlane calculate_F(SDoublePlane D, SDoublePlane &binary_template, double threshold) {
double sum = 0.0;
int m = binary_template.rows(), n = binary_template.cols();
int i, j, k, l, input_rows = D.rows(), input_cols = D.cols();
SDoublePlane output(input_rows, input_cols);
for(i=0; i<input_rows - m; i++){
for(j=0; j<input_cols - n; j++){
sum=0.0;
for(k =0; k<m; k++){
for(l=0; l<n; l++){
sum += binary_template[k][l] * D[i+k][j+l];
}
}
output[i][j] = sum;
}
}
//converting low scores to white n others black
for(i=0; i<input_rows - m; i++)
for(j=0; j<input_cols - n; j++)
if(output[i][j] < threshold){
output[i][j] = 255;
}
else
output[i][j] = 0;
return output;
}
SDoublePlane compute_pairwise_cost(SDoublePlane disp, SDoublePlane &labels, int i, int j) {
int sum = 0;
int min_diff = INT_MAX;
int min_label = DLIMIT;
SDoublePlane result(disp.rows(), disp.cols());
// for (int i = 1; i < disp.rows() - 1; i++) {
// for (int j = 1; j < disp.cols() - 1; j++) {
min_diff = INT_MAX;
for (int d = 0; d < DLIMIT; d++) {
sum = 0;
sum += pow(d - disp[i][j - 1], 2);
sum += pow(d - disp[i][j + 1], 2);
sum += pow(d - disp[i + 1][j], 2);
sum += pow(d - disp[i - 1][j], 2);
if (sum < min_diff) {
min_diff = sum;
min_label = d;
}
}
result[i][j] = min_diff;
disp[i][j] = min_label;
//cout<<min_diff<<endl;
// }
// }
return result;
}
HammingDistances find_hamming_distance(SDoublePlane &img_input, SDoublePlane &img_template){
int input_rows = img_input.rows();
int input_cols = img_input.cols();
int template_rows = img_template.rows();
int template_cols = img_template.cols();
HammingDistances hm;
double sum = 0.0;
double max_hamming = 0.0;
SDoublePlane output(input_rows, input_cols);
for(int i =0;i<input_rows - template_rows ; ++i){
for(int j =0;j<input_cols - template_cols; ++j){
sum=0.0;
for(int k =0;k<template_rows;++k){
for(int l=0;l<template_cols;++l){
sum = sum + (img_input[i+k][j+l] * img_template[k][l] + (1 - img_input[i+k][j+l])*(1 - img_template[k][l]));
}
}
output[i][j] = sum;
if(sum>max_hamming)
max_hamming = sum;
}
}
//printImg2File("input_img_file_Output.txt", img_input);
//printImg2File("img2fileOutput.txt", output);
hm.hamming_matrix = output;
hm.max_hamming_distance= max_hamming;
return hm;
}
SDoublePlane calculate_D(SDoublePlane &binary_image_blur_sobel) {
int i, j, input_rows = binary_image_blur_sobel.rows(), input_cols = binary_image_blur_sobel.cols();
SDoublePlane D(input_rows, input_cols);
//initialize edges as 0 and others as infinity(10000) in binary_image_blur_sobel
for(i=0;i<input_rows;i++)
for(j=0;j<input_cols;j++)
if(binary_image_blur_sobel[i][j] == 1)
D[i][j] = 0;
else
D[i][j] = 10000;
//distance below and to the right of edges
for(i=1;i<input_rows;i++)
for(j=1;j<input_cols;j++)
D[i][j] = dmin(D[i][j], D[i][j-1]+1, D[i-1][j]+1);
//distance above and to the left of edges
for(i=input_rows-2; i>=0; i--)
for(j=input_cols-2; j>=0 ;j--)
D[i][j] = dmin(D[i][j], D[i+1][j]+1, D[i][j+1]+1);
//bottom row
i = input_rows-1;
for(j=input_cols-2; j>=0 ;j--)
D[i][j] = dmin(D[i][j], D[i-1][j]+1, D[i][j+1]+1);
//rightmost column
j = input_cols-1;
for(i=input_rows-2; i>=0; i--)
D[i][j] = dmin(D[i][j], D[i+1][j]+1, D[i][j-1]+1);
return D;
}
//using the normalized votes find the best row co-ordinates for staff lines
SDoublePlane find_best_line_intercepts(const SDoublePlane &row_votes,const SDoublePlane &normed_votes,int best_space,double norm_threshold=0.55,int neighbour_threshold=4,int start=0)
{
SDoublePlane row_spacing=row_votes;
if(start < row_votes.rows()){
SDoublePlane staff_lines(row_votes.rows(),1);
int i=0;
double best_value=0;
int intercept_value=0;
while(i<row_votes.rows()){
if(normed_votes[i][0] > norm_threshold){
best_value=normed_votes[i][0];
intercept_value=i;
for(int j=1;j<neighbour_threshold;j++){
if(normed_votes[i+j][0] > best_value ){
best_value=normed_votes[i+j][0];
intercept_value=i+j;
}
}
row_spacing=set_staff(row_spacing,best_space,intercept_value,start);
i=intercept_value+(4*(best_space))+neighbour_threshold;
start=intercept_value+(4*best_space)+neighbour_threshold;
}
i++;
}
}
return row_spacing;
}
// Apply an edge detector to an image, returns the binary edge map
SDoublePlane find_edges(const SDoublePlane &input, double thresh = 0) {
SDoublePlane output(input.rows(), input.cols());
// Implement an edge detector of your choice, e.g.
// use your sobel gradient operator to compute the gradient magnitude and threshold
return output;
}
SDoublePlane scale_image(const SDoublePlane &input, double ratio)
{
int m = input.rows();
int n = input.cols();
int m2 = input.rows()*ratio;
int n2 = input.cols()*ratio;
SDoublePlane output(m2, n2);
if (ratio > 0.5)
{
for (int i = 0; i < m2; i++)
{
int sk = i/ratio;
int ek = (i + 1)/ratio - 0.00001;
for (int j = 0; j < n2; j++)
{
int sl = j/ratio;
int el = (j + 1)/ratio - 0.00001;
output[i][j] = input[sk][sl];
output[i][j] += input[sk][el];
output[i][j] += input[ek][sl];
output[i][j] += input[ek][el];
output[i][j] /= 4.0;
}
}
}
else
{
int span = 1.0/ratio + 0.5;
for (int i = 0; i < m2; i++)
{
int sk = i/ratio;
int ek = (i - 1)/ratio - 0.00001;
for (int j = 0; j < n2; j++)
{
int sl = j/ratio;
int el = (j - 1)/ratio - 0.00001;
output[i][j] = 0;
for (int u = sk; u <= ek; u++)
{
for (int v = sl; v <= el; v++)
{
output[i][j] += input[u][v];
}
}
output[i][j] /= (ek - sk + 1)*(el - sl + 1);
}
}
}
return output;
}
SDoublePlane normalize_votes(const SDoublePlane &acc)
{
SDoublePlane normalized(acc.rows(),acc.cols());
double min = find_min_vote(acc);
double max = find_max_vote(acc);
for(int i=0;i<acc.rows();i++){
normalized[i][0] = (acc[i][0] - min)/(max-min);
}
return normalized;
}
void print_image_value(const SDoublePlane &input)
{
for (int i = 0; i < input.rows(); ++i)
{
for (int j = 0; j < input.cols(); ++j)
{
cout << input[i][j] << " ";
}
cout << endl;
}
}
SDoublePlane complement_image(const SDoublePlane &input)
{
SDoublePlane output(input);
for (int i = 0; i < input.rows(); ++i)
{
for (int j = 0; j < input.cols(); ++j)
{
output[i][j] = 255 - output[i][j];
}
}
return output;
}
// Print an image to a file
void printImg2File(string filename, SDoublePlane img) {
ofstream outFile;
outFile.open(filename.c_str());
for (int i = 0; i < img.rows(); i++) {
for (int j = 0; j < img.cols(); j++) {
outFile << img[i][j] << ",";
}
outFile << "\n";
}
outFile.close();
}
// The rest of these functions are incomplete. These are just suggestions to
// get you started -- feel free to add extra functions, change function
// parameters, etc.
//
//
// Print the value of the image
//
void print_image_value1(const SDoublePlane &input)
{ int sum=0;
for (int i = 0; i < input.cols(); ++i)
{ sum=0;
for (int j = 0; j < input.rows(); ++j)
{ sum=sum+input[j][i];
//cout << input[i][j] << " ";
}
//cout << endl;
cout<<sum<<"|||"<<i<<endl;
}
}
// Find symbols in the given image for the given template
void find_symbols(HammingDistances hm, SDoublePlane input, SDoublePlane img_template, vector <DetectedSymbol> &symbols, Type symbol_type){
int template_rows = img_template.rows();
int template_cols = img_template.cols();
double max_hamming_distance = hm.max_hamming_distance;
SDoublePlane matrix = hm.hamming_matrix;
vector<LineLocation> allLinesLocVector;
double confidence_threshold;
if (symbol_type == NOTEHEAD){
confidence_threshold = 0.9;
allLinesLocVector = find_line_location(input);
}
else
confidence_threshold = 0.95;
// Finding symbols
for(int i =0;i<matrix.rows();i++){
for(int j=0;j<matrix.cols();j++){
double value = matrix [i][j];
if( value >= confidence_threshold * max_hamming_distance) {
DetectedSymbol s;
s.row = i;
s.col = j;
s.width = template_cols;
s.height = template_rows;
s.type = symbol_type;
s.confidence = value;
s.pitch = ' ';
if(symbol_type == NOTEHEAD)
set_symbol_marker(s, allLinesLocVector);
else
s.pitch = ' ';
symbols.push_back(s);
// Marking the pixels of the template so that they are not detected again
for (int x=i; x < i+s.height; x++){
for (int y=j; y < j+s.width; y++){
matrix[x][y] = -100;
}
}
}
}
}
}
SDoublePlane normalize_image(const SDoublePlane &input)
{
SDoublePlane output(input);
double max = image_max(output);
double min = image_min(output);
for (int i = 0; i < input.rows(); ++i)
{
for (int j = 0; j < input.cols(); ++j)
{
output[i][j] = (output[i][j] - min) / (max - min) * 255;
}
}
return output;
}
// Resize image
SDoublePlane resize_image(SDoublePlane &input, double newScaleRatio)
{
if (newScaleRatio == 1) return input;
int rows = input.rows();
int cols = input.cols();
int newWidth = newScaleRatio * cols;
int newHeight = newScaleRatio * rows ;
SDoublePlane output(newHeight, newWidth);
set<int> mySetRows;
while( mySetRows.size() < newHeight ){
mySetRows.insert( rand()% rows +1 );
}
set<int> mySetCols;
while( mySetCols.size() < newWidth ){
mySetCols.insert( rand()% cols+1 );
}
int ii =0;
for(int i = 1; i <rows;i++){
if(mySetRows.find(i) == mySetRows.end()){
continue;
}
int jj=0;
for(int j = 1; j<cols;j++){
if(mySetCols.find(j) == mySetCols.end())
{
continue;
}
if(i<rows-1 && j<cols-1){
output[ii][jj] = (input[i][j] + input [i+1][j] + input[i][j+1] + input[i+1][j+1])/4;
}
jj++;
}
ii++;
}
//write_detection_image("Resized_pic.png", output);
return output;
}
// Hough Transform
// Inspired by Lecture from Prof. William Hoff, Colorado School of Mines, Engineering Division
// https://www.youtube.com/watch?v=o-n7NoLArcs and http://goo.gl/TxbGWi
//
SDoublePlane runHoughTransform(SDoublePlane &img){
//printImg2File("sobelPNG.txt",img);
int r = img.rows();
int c = img.cols();
double hough_height;
// Initialize Accumulator matrix
if (r>c)
hough_height = r / sqrt(2);
else
hough_height = c / sqrt(2);
int maxDist = round(hough_height * 2);
int theta = 180;
double rho,t;
int iRho;
SDoublePlane H(maxDist, theta);
for (int i = 0; i < maxDist; i++)
for (int j = 0; j < theta; j++)
H[i][j] = 0;
double center_x = c/2;
double center_y = r/2;
for (int i = 0; i < r; i++) {
for (int j = 0; j < c; j++) {
if (img[i][j] > 250){
// Fill accumulator array
for (int iTheta = 0 ; iTheta < theta ; iTheta++){
// Getting angle in radians
t = iTheta * M_PI / 180;
// Calculate distance from origin for this angle
rho = ( j - center_x) * cos (t) + ( i - center_y) * sin(t);
iRho = int(round(rho + hough_height));
H[iRho][iTheta]++;
}
}
}
}
return H;
}
double image_min(const SDoublePlane &input)
{
double min=0;
for (int i = 0; i < input.rows(); ++i)
{
for (int j = 0; j < input.cols(); ++j)
{
if (input[i][j] < min)
{
min = input[i][j];
}
}
}
return min;
}
double image_max(const SDoublePlane &input)
{
double max=0;
for (int i = 0; i < input.rows(); ++i)
{
for (int j = 0; j < input.cols(); ++j)
{
if (input[i][j] > max)
{
max = input[i][j];
}
}
}
return max;
}
SDoublePlane display_binary(SDoublePlane &input){
int rows = input.rows();
int cols = input.cols();
SDoublePlane output(rows,cols);
for(int i= 0; i<rows; ++i)
for(int j=0; j<cols; ++j){
if(input[i][j] < 0.3)
output[i][j] = 0;
else
output[i][j] = 255;
}
return output;
}
SDoublePlane convert_blur_to_binary(SDoublePlane &input){
int rows = input.rows();
int cols = input.cols();
SDoublePlane output(rows,cols);
for(int i= 0; i<rows; ++i)
for(int j=0; j<cols; ++j){
if(input[i][j] < 1)
output[i][j] = 0;
else
output[i][j] = 1;
}
return output;
}
SDoublePlane compute_distance_matrix(SDoublePlane &edge_map)
{
SDoublePlane D(edge_map.rows(), edge_map.cols());
// Do a dijkstra in O(nlgn), n=total number of pixel in edge_map
priority_queue< pair<int,double>, vector< pair<int,double> >, compare_priority_queue> Q;
const int n_col = D.cols();
const int n_row = D.rows();
for (int i = 0; i < n_row; ++i)
{
for (int j = 0; j < n_col; ++j)
{
if ( edge_map[i][j] > 0.1)
{
D[i][j] = 0;
Q.push(make_pair(i*n_col+j, 0.0));
}
else
D[i][j] = -1;
}
}
while (Q.empty() == false)
{
pair<int,double> u = Q.top();
int row = u.first / n_col;
int col = u.first % n_col;
double w;
Q.pop();
for (int i = -1; i <= 1; ++i)
{
for (int j = -1; j <= 1; ++j)
{
if (row+i<0 || row+i>=n_row || col+j<0 || col+j>=n_col || (i==0 && j==0))
continue;
w = (i*j==0?1:1.414);
if ( abs(D[row+i][col+j]+1) < 0.0001 || D[row+i][col+j] > D[row][col] + w)
{
D[row+i][col+j] = D[row][col] + w;
Q.push( make_pair( (row+i)*n_col+(col+j), D[row+i][col+j] ) );
}
}
}
}
return D;
}
SDoublePlane convert_BW(SDoublePlane &input){
int rows = input.rows();
int cols = input.cols();
SDoublePlane output(rows,cols);
double threshold = 100.0;
for(int i= 0;i<rows;++i)
for(int j=0;j<cols;++j){
if(input[i][j] >= threshold || input[i][j] == 1)
output[i][j] = 255;
else
output[i][j] =0;
}
return output;
}
//from the row co-ordinates/best space matrix find the space parameter with high votes
int find_best_spacing(const SDoublePlane &row_spacing)
{
long max=0,sum=0;
int best_space=0;
for(int i=2;i<row_spacing.cols();i++){
sum=0;
for(int j=0;j<row_spacing.rows();j++){
sum=sum+row_spacing[j][i];
}
if(sum > max){
max=sum;
best_space=i;
}
}
return best_space;
}