//==============================================================================
//==============================================================================
//==============================================================================
//==============================================================================
//==============================================================================
//==============================================================================
void
patch_models::
train(ft_data &data,
const vector<Point2f> &ref,
const Size psize,
const Size ssize,
const bool mirror,
const float var,
const float lambda,
const float mu_init,
const int nsamples,
const bool visi)
{
//set reference shape
int n = ref.size(); reference = Mat(ref).reshape(1,2*n);
Size wsize = psize + ssize;
//train each patch model in turn
patches.resize(n);
for(int i = 0; i < n; i++){
if(visi)cout << "training patch " << i << "..." << endl;
vector<Mat> images(0);
for(int j = 0; j < data.n_images(); j++){
Mat im = data.get_image(j,0);
// imshow("im",im);
vector<Point2f> p = data.get_points(j,false);
Mat pt = Mat(p).reshape(1,2*n);
Mat S = this->calc_simil(pt),A(2,3,CV_32F);
A.fl(0,0) = S.fl(0,0); A.fl(0,1) = S.fl(0,1);
A.fl(1,0) = S.fl(1,0); A.fl(1,1) = S.fl(1,1);
A.fl(0,2) = pt.fl(2*i ) -
(A.fl(0,0) * (wsize.width-1)/2 + A.fl(0,1)*(wsize.height-1)/2);
A.fl(1,2) = pt.fl(2*i+1) -
(A.fl(1,0) * (wsize.width-1)/2 + A.fl(1,1)*(wsize.height-1)/2);
Mat I; warpAffine(im,I,A,wsize,INTER_LINEAR+WARP_INVERSE_MAP);
images.push_back(I);
if(mirror){
im = data.get_image(j,1);
p = data.get_points(j,true);
pt = Mat(p).reshape(1,2*n);
S = this->calc_simil(pt);
A.fl(0,0) = S.fl(0,0); A.fl(0,1) = S.fl(0,1);
A.fl(1,0) = S.fl(1,0); A.fl(1,1) = S.fl(1,1);
A.fl(0,2) = pt.fl(2*i ) -
(A.fl(0,0) * (wsize.width-1)/2 + A.fl(0,1)*(wsize.height-1)/2);
A.fl(1,2) = pt.fl(2*i+1) -
(A.fl(1,0) * (wsize.width-1)/2 + A.fl(1,1)*(wsize.height-1)/2);
warpAffine(im,I,A,wsize,INTER_LINEAR+WARP_INVERSE_MAP);
images.push_back(I);
}
}
patches[i].train(images,psize,var,lambda,mu_init,nsamples,visi);
}
}
void
draw_connections(){
int m = data.connections.size();
if(m == 0)this->draw_points();
else{
if(data.connections[m-1][1] < 0){
int i = data.connections[m-1][0];
data.connections[m-1][1] = i;
data.draw_connect(image,idx); this->draw_points();
circle(image,data.points[idx][i],1,CV_RGB(0,255,0),2,CV_AA);
data.connections[m-1][1] = -1;
}else{data.draw_connect(image,idx); this->draw_points();}
}
}
void
draw_points(){
data.draw_points(image,idx);
}
int
set_current_image(const int idx = 0){
if((idx < 0) || (idx > int(data.imnames.size())))return 0;
image = data.get_image(idx,2); return 1;
}
//==============================================================================
void
face_detector::
train(ft_data &data,
const string fname,
const Mat &ref,
const bool mirror,
const bool visi,
const float frac,
const float scaleFactor,
const int minNeighbours,
const Size minSize)
{
detector.load(fname.c_str()); detector_fname = fname; reference = ref.clone();
vector<float> xoffset(0),yoffset(0),zoffset(0);
for(int i = 0; i < data.n_images(); i++){
Mat im = data.get_image(i,0); if(im.empty())continue;
vector<Point2f> p = data.get_points(i,false); int n = p.size();
Mat pt = Mat(p).reshape(1,2*n);
vector<Rect> faces; Mat eqIm; equalizeHist(im,eqIm);
detector.detectMultiScale(eqIm,faces,scaleFactor,minNeighbours,0
|CV_HAAR_FIND_BIGGEST_OBJECT
|CV_HAAR_SCALE_IMAGE,minSize);
if(faces.size() >= 1){
if(visi){
Mat I; cvtColor(im,I,CV_GRAY2RGB);
for(int i = 0; i < n; i++)circle(I,p[i],1,CV_RGB(0,255,0),2,CV_AA);
rectangle(I,faces[0].tl(),faces[0].br(),CV_RGB(255,0,0),3);
imshow("face detector training",I); waitKey(10);
}
//check if enough points are in detected rectangle
if(this->enough_bounded_points(pt,faces[0],frac)){
Point2f center = this->center_of_mass(pt); float w = faces[0].width;
xoffset.push_back((center.x - (faces[0].x+0.5*faces[0].width ))/w);
yoffset.push_back((center.y - (faces[0].y+0.5*faces[0].height))/w);
zoffset.push_back(this->calc_scale(pt)/w);
}
}
if(mirror){
im = data.get_image(i,1); if(im.empty())continue;
p = data.get_points(i,true);
pt = Mat(p).reshape(1,2*n);
equalizeHist(im,eqIm);
detector.detectMultiScale(eqIm,faces,scaleFactor,minNeighbours,0
|CV_HAAR_FIND_BIGGEST_OBJECT
|CV_HAAR_SCALE_IMAGE,minSize);
if(faces.size() >= 1){
if(visi){
Mat I; cvtColor(im,I,CV_GRAY2RGB);
for(int i = 0; i < n; i++)circle(I,p[i],1,CV_RGB(0,255,0),2,CV_AA);
rectangle(I,faces[0].tl(),faces[0].br(),CV_RGB(255,0,0),3);
imshow("face detector training",I); waitKey(10);
}
//check if enough points are in detected rectangle
if(this->enough_bounded_points(pt,faces[0],frac)){
Point2f center = this->center_of_mass(pt); float w = faces[0].width;
xoffset.push_back((center.x - (faces[0].x+0.5*faces[0].width ))/w);
yoffset.push_back((center.y - (faces[0].y+0.5*faces[0].height))/w);
zoffset.push_back(this->calc_scale(pt)/w);
}
}
}
}
//choose median value
Mat X = Mat(xoffset),Xsort,Y = Mat(yoffset),Ysort,Z = Mat(zoffset),Zsort;
cv::sort(X,Xsort,CV_SORT_EVERY_COLUMN|CV_SORT_ASCENDING); int nx = Xsort.rows;
cv::sort(Y,Ysort,CV_SORT_EVERY_COLUMN|CV_SORT_ASCENDING); int ny = Ysort.rows;
cv::sort(Z,Zsort,CV_SORT_EVERY_COLUMN|CV_SORT_ASCENDING); int nz = Zsort.rows;
detector_offset = Vec3f(Xsort.fl(nx/2),Ysort.fl(ny/2),Zsort.fl(nz/2)); return;
}
