FACIAL DETECTION IMPLEMENTATION USING PRINCIPAL COMPONENT ANALYSIS (PCA)
Pilaka Anusha, Kaki Leela Prasad, Gande Ravi Kumar, E. Laxmi Lydia, Velmurugan Subbiah Parvathy · Journal of Critical Reviews · 2020
A facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from a video source. One of the ways to do this is by comparing selected facial features from the image and a facial database. It is used in security features and can be compared to other biometrics, fingerprint or iris recognition systems. Face Recognition is helpful in many ways like checking criminal records, enhancement of security, pattern recognition etc. This project mainly focuses on recognizing faces using Principal Component Analysis(PCA). It is a way of identifying patterns in data, and expressing the data in such a way as to highlight their similarities and differences and also compress data. In this method, facial features are transformed in eigenspace using Principal Component Analysis, which is able to classify individual facial representations. Thus, trained faces have some Eigen values and weight. In order to identify faces, test images are compared with trained images. So, by comparing the weight (w) of an image with test images, we can recognize the actual face. The images are compared on the basis of eigenvalues and images with unique values are stored else they are discarded.