DEVELOPMENT OF BIOMETRIC FACE RECOGNITION SYSTEM

Computer Sciene

The proposed system develops the face recognition system by using Principal Component Analysis (PCA) Algorithm PCA relies on the singular value decomposition (SVD) of rectangular matrices and the Eigen-decomposition of positive semi-definite matrices. It is decided by the Eigen values and eigenvectors. Numbers make up eigenvectors and eigen values. as well as the vectors connected to square matrices. Together, they offer the Eigen-decomposition of a matrix, which examines its structure, including any cross-product, correlation, or covariance matrices. In practice, PCA is relatively easy to perform. An m n matrix, where m is the number of measurement kinds and n is the number of trials, should be used to organize a data set. For each measurement type, subtract the mean, or row xi. Determine the SVD or the covariance's eigenvectors. It was discovered that PCA had a variety of fascinating uses. For Face Biometric system we used The P.C.A. (Principal Component Analysis) based feature extraction system and Euclidean distance matcher. The accuracy for the face modality is 90 .4% and FAR is 5.06 % FRR is 7.09%. The Recognition rate is also improved using advanced pattern recognition and NN techniques, which will be studied in future.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.