Patch-based pose invariant face feature classification

Abstract

Real world face recognition systems are now successfully developed to recognise faces in frontal view. One of the most challenging tasks facing state-of-the-art face recognition algorithms is how to handle variations caused by the direction of the face image in terms of angles, that are between the probe and the gallery images. This research work treats the problem caused by variations in pose as a classi cation problem. We conduct face classi cation on the FERET database. Firstly, we extract the SIFT features at di erent scale spaces ( ); by extracting these features at di erent levels will help us determine which values of ( ) give a better representation of our data. Secondly, we train these features using four machine-learning algorithms: k-Nearest Neighbor (kNN), Support Vector Machine (SVM), decision trees and neural network pattern recognition. The experiments demonstrate that by increasing the blur ( ) parameter, the classi cation rate decreases.