Face Recognition using Tchebichef Moments

Abstract

In this paper, a new Face Recognition method based on Discrete orthogonal Tchebichef moments with Linear Discriminant Analysis and Probabilistic Neural Network is proposed. Tchebichef moments are having good energy compaction property that made them useful in image compression and dimensionality reduction operations. Moreover the translation and scale invariant properties of Tchebichef moments are very much useful in almost all pattern recognition applications. The proposed face recognition method consists of three steps, i) Dimensionality reduction using Tchebichef moments ii) Feature extraction using Linear Discriminant Analysis and iii) classification using Probabilistic Neural Network. Linear Discriminant Analysis selects features that are most effective for class seperability in addition to dimensionality reduction. Combination of Tchebichef moments and Linear Discriminant Analysis is used for improving the capability of Linear Discriminant Analysis when few samples of images are available. Probabilistic Neural network (PNN) is a promising tool and gives fast and accurate classification of face images. Evaluation was performed on two face data bases. First database of 400 face images from Olivetty Research Laboratories (ORL) face database, and the second database of thirteen students are taken. The proposed method gives fast and better recognition rate when compared to other classifiers. The main advantage of this method is its high speed processing capability and low computational requirements.