Abstract
This paper presents a pose invariant face recognition system to annihilate pose problem by using a modified log Gabor algorithm and the concepts of rough sets together. The proposed system consists of four separate modules; face detection, pose classification, feature extraction and recognition. Rough membership function (rmf) classifier has been used to classify the poses of an image. Log Gabor has been used as feature extraction to represent the face and SVDs to reduce the redundant features. And at last, the reduced log Gabor feature is applied to the nearest neighbour classifier for recognition. The aim of this paper is to address the issues such as recognizing the individual from mug shot images, under limited number of training samples available for large degree of variations in poses. The proposed system has been evaluated for different pose variations under arbitrary tilt orientations for four different face databases.