Face Detection and Recognition Using PCA for Rehabilitant

초록

In this paper, we developed a computer system that can locate and track a subjects head in a complex background and then recognize the person by comparing characteristics of the face to those of individuals. The proposed method is based on the color information and eigenface of PCA-LDA(Principal Component Analysis Linear Discriminant Analysis). In PCA-LDA method, the features are obtained through eigenvector analysis of scatter matrices with the objective of maximizing between-class variations and minimizing within-class variations. The system functions are composed to two steps. First step is extracting face image in a complex background using color model, and second, projecting pre-extracted face images onto a feature space that represents the significant variations among known face images. We use this weight vector to recognize each individual. The experimental result with the proposed method is more accurate and more computation efficient in comparing with the original PCA(Principal Component Analysis). This system, automatic face recognition, can apply to many rehabilitant certification fields. Especially, it is very useful for the equipment which are used for between rehabilitants and normal persons.