YCbCr Technique based Human Face Recognition

Face detection is a necessary first-step in face recognition systems, with the reason of localize and extract the face region from the background. It also has a number of applications in areas such as content-based image recovery, video coding, video conferencing, crowd observation, and intelligent human–computer interfaces. We have taken skin color as a tool for detection. This technique works well for all types’ faces which have a specific complexion varying under definite range. We have taken real life examples and simulated the algorithms in MATLAB successfully. This paper concentrates on the input images are converted to the YCbCr model to collect the value Y,Cb,Cr. and check whether these values are satisfied with the threshold values. If the pixels are in the range of threshold then that pixels will be considered as skin region otherwise it is a non skin region. This paper defined algorithm has been tested on various real time frontal images and gets better results for the YCbCr color model.