Convolution Based Face Recognition Using DWT and HOG

Abstract

Physiological face biometric trait is used to identify a person for many real time applications. The convolution based feature extraction technique for face identification using Discrete Wavelet Transform (DWT) and Histogram of Oriented Gradient (HOG) is proposed to recognize human beings effectively. The four standard face databases with different sizes are considered and resized to $128\mathrm{X}128$ to have uniform size of images. The 2D-DWT (Two Dimensional Discrete Wavelet Transform) is applied on resized face images and considered only (LL) sub-band. The HOG is applied on LL subband to obtain HOG coefficients. The 2D convolution is used on LL sub-band and HOG matrix to obtain final features. The resized face image is compressed using DWT and HOG. The Euclidean distance(ED) is used to compare features of database face images with test images to compute performance parameters. The performance of the proposed method is better than the existing methods.