Biometric Authentication based on Detection and Recognition of Multiple Faces in Image

Biometric Authentication works on some human characteristics, such as, finger print, voice, pattern of lines in the iris of eye or face. I represent a multiple face detection method based on skin color information and the Lines of Separability (LS) face model and recognition method based on principle component analysis and neural network. Face detection method uses YCbCr color model and sigma control limits for variation in its color components. Faces are extracted from the images. The face space is described by a set of eigenfaces. Each face is efficiently represented by its projection onto the space expanded by the eigenfaces and new descriptor. After face detection stage neural network are used for face recognition. A system is implemented which detects multiple faces in an image and recognizes it.