iphone - detect objects of any shape from image and color individual object -


i new opencv , doing detect different objects image , apply effects on individual object. find edges, , using following code contours, how how proceed ahead dont know. ???? in advance

cv::mat edges; cv::canny(gray, edges, 50, 150);  std::vector< std::vector<cv::point> > c; std::vector<cv::point> points; cv::findcontours(edges, c, cv_retr_list, cv_chain_approx_none); cv::mat mask = cv::mat::zeros(edges.rows, edges.cols, cv_8uc1);   (size_t i=0; i<c.size(); i++)    {    (size_t j = 0; j < c[i].size(); j++)    {     cv::point p = c[i][j];     points.push_back(p);     // printf(" %d \t",p.x);    }   } cv::mat crop(inputframe.rows, inputframe.cols, cv_8uc3); inputframe.copyto(outputframe, mask); 

since have chosen identify objects through contour, suggest continue "generalized hough transform" (pdf). have create reference contours objects, want recognize (from every conceivable viewpoint).

another option, might interesting segmentation algorithms in order select objects in image. without knowing objects, looking , images processing, impossible give recommendations. there no general purpose algorithm works on every image (at least far know).

to give idea state-of-the-art object class recognition, can have @ pascal voc challenge. if problem simpler challenge (e.g. small set of immutable objects, stand in front of 1 colored background), should specify in question, , maybe can give better suggestions.


Comments

Popular posts from this blog

Why does Ruby on Rails generate add a blank line to the end of a file? -

keyboard - Smiles and long press feature in Android -

node.js - Bad Request - node js ajax post -