0

I am currently implementing a detection and tracking system by tracking heads. I was trying to figure out some similarity score between two detected images so that I can analyse if the detections are of the same person or not (in different frames). I tried to change the RGB images (detections) into HSV and concatenate the Hue and Saturation values into one single vector for each image. Then I found the difference between the vectors of the separate detections by using the summation of the absolute difference.

However, when I tried it, a detection of a bag had a better similarity score than that of the same head. Can someone guide me with what maybe is wrong or else any better comparison technique?

Sambas23
  • 683
  • 1
  • 13
  • 27
  • 1
    An [mcve](http://stackoverflow.com/help/mcve) would be good. otherwise I think this question is too broad. – kkuilla Feb 25 '15 at 14:16
  • if you are trying to achieve face recognition (which I think you do) comparing HSV values is not the way to go. Look online for face recognition algorithms. The simplest would probably be Eigen Faces, but there are many others – Rosa Gronchi Feb 25 '15 at 15:34
  • I am actually doing Head detection comparison...I posted a new question here [link](http://stackoverflow.com/questions/28723670/intersection-over-union-between-two-detections) – Sambas23 Feb 25 '15 at 16:01

0 Answers0