This paper presents a method that combines colour and motion information to track pedestrians in video sequences captured by a fixed camera. Pedestrians are firstly detected using the human detector proposed by Dalal and Triggs which involves com

Code takes two images-detect faces-transform them into feature with LBP-calculates histogram according to LBP codes and compare histograms you can change the parameters that how many pieces you want to fall the face to or change LBP parameters