Haar Cascade Object Detection Face & Eye - OpenCV with Python for Image and Video Analysis 16
Haar face detection is very slow. In order to improve the performance and to increase the detection process. I used some addtional steps.. 1. save the face locations detected in previews frame, and in current frame it only scan the area near them. If no face is detected in previews frame, scan the whole picture.
This approche is good for single face detection but improper to multi face detection. Consider this situation: one man goes into screen while there is already another face be detected, so he's face will not in the scan area, he will not be detected. So I think maybe I need scan the whole picture not only when no face is detected ,and also do full scanning at regular intervals.
Do you any other good ideas?
You must be logged in to post. Please login or register an account.