Face Recognition System Based on Wavelet Transform,Histograms of Oriented Gradients and Support Vector Machine

Abstract

Face recognition is a well-known image analysis application in the fields of pattern recognition and computer vision. It utilizes the uniqueness of human facial characteristics for personnel identification. The paper in hand presents a facial recognition system that uses facial features and Support Vector Machine (SVM) to achieve accurate recognition. The image processing happens with histogram equalization, also utilizing a median filter for pre-processing. A combination of wavelet transforms and Histograms of Oriented Gradients (HOG), extracts the feature vector, which produces a reliable performance. Dimensionality reduction happens by applying Principal Component Analysis (PCA). Finally, by applying the Support Vector Machine (SVM), face classification happens. Experimental development happened on the Yale database of 165 images from 15 individuals in a MATLAB environment. The testing proved the accuracy of 98.64% percentage of success with acceptable speed, and it confirmed the accuracy and robustness of the proposed system.