Multidimensional histograms can also be backprojected onto an image. Let's define a class that encapsulates the backprojection process. First, we define the required attributes and initialize the data, as follows:
class ContentFinder {
private:
// histogram parameters
float hranges[2];
const float* ranges[3];
int channels[3];
float threshold; // decision threshold
cv::Mat histogram; // input histogram
public:
ContentFinder() : threshold(0.1f) {
// in this class, all channels have the same range
ranges[0]= hranges;
ranges[1]= hranges;
ranges[2]= hranges;
}
Next, we define a threshold parameter that will be used to create the binary map that shows the detection result. If this parameter is set to a negative ...
