Color images face recognition based on multi-classification support vector machine

Skin color information plays an important role in face detection and recognition. By a large number of skin pixels statistics, the model of face skin color information is constructed in YUV and YCbCr color spaces. The Mahalanobis distance map of the image is obtained to extract features and establish Eigenfaces space. A novel Support Vector Machine method based on error-correcting codes matrix is proposed. The algorithm is loop-arranged and symmetrical divided classes of multi-classification problem, and the class of an unknown sample is obtained by the decode function based on error-correcting codes matrix. Experimental results demonstrate that using YCbCr color information and a new SVM in face recognition is effective.