HOG & Sparse Based Face Recognition System
Shahina Shahina, Arun P.S · IOSR Journal of VLSI and Signal processing · 2016
Face detection and recognition is one of the most challenging problems in the field of image processing.One of the recent techniques in face recognition is by the sparse representation.In this paper, combination of Sparse and Histogram of Oriented Gradients (HOG) are used.In the first stage dimensionality reduction is done to reduce the amount of random variables and the features are extracted using Principal Component Analysis (PCA).The extracted features are classified using Sparse Representation via 𝑙 1minimization.For better invariance to illumination and expression changes, Histogram of Oriented Gradients (HOG) feature is also extracted to represent face images.This method offer the better recognition performance when compared to the existing methods.The proposed face recognition method is evaluated on the standard ORL data base and yields very impressive results.