Face recognition using Eigen-Face implemented on DSP processor

Abstract

Face recognition is the established research area in 2D biometric recognition system and broadly used in a security system. Face recognition system is a physiological biometric information processing based on the two dimensional face image. This thesis focus to develop an automatic face recognition using holistic features extracted that use the global features represented by low frequency data from face image. Holistic features are extracted using eigenface method where a linear projection technique such as PCA is used to capture the important information in the image. Face image has low frequency information such as shape of mouth, eye, and nose which has high discrimination power. By using PCA, only several number of eigenvector is preserved which belong to these features. A low dimensional feature space is classified using distance classifier. Distance classifier is used to calculate the similarity between two data points in the feature space based on the distance of two vectors. Euclidean distance is used for matching process. The propose method is tested using a benchmark ORL dataset that has 400 images of 40 persons. The best recognition rate is 97.5% when tested using 9 training images and 1 testing image represented with 35 PCA coefficients. Using less number of PCA coefficients is able for the classifier module to be implemented using hardware such as DSP processor. Euclidean distance classifier is tested using the TMS320C6713 digital signal processor (DSP). The computational time is less compared with the offline simulation using PC based.