Multimodal face recognition using multidimensional clustering on hyperspectral face images

Human face is a very common biometric trait, with advancement of technology it is possible to capture face images in hyperspectral range. With the availability of such hyperspectral face data it is possible to build systems biometrics authentication systems working in hyperspectral range. Main focus current research is to use hyperspectral face images for biometric authentication. Hyperspectral face images with 33 band are used for generation of feature vector based on Vector Quantization (VQ) process. Popular VQ Algorithms like Kekre's Fast Codebook Generation (KFCG) Algorithm and Kekre's Median Codebook Generation (KMCG) Algorithm are used to generate codebooks. This feature vector is used for identification of the person. K-Nearest Neighborhood classifier (K-NN) is be used and performance is evaluated. Here the study is extended for Multimodal Implementation also, by combining Left, Right face samples feature vectors. The score fusion technique is implemented on front, left and right face images and the effect of fusion is studied.