A novel method for color face recognition using KNN classifier

Recently face recognition has become an important area of research in computer vision, neuroscience, and psychology. In this paper a new color face recognition (FR) method is introduced. The effectiveness of color information plays an important role when face images are taken under strong variations in illumination, as well as with low spatial resolutions. The proposed method has 3 steps. In the first step the input color image is converted into various color space models. In the second step eigen values and eigen vectors are extracted from each color space models. In the final step a nearest neighbour classifier is designed for classifying the face images based on the extracted features. The accuracy of proposed method is impressively better than the results of other FR methods over different FR challenges including highly uncontrolled illumination, moderate pose variation, and small resolution face images.