Modified LDA classifier in multi resolution wavelet domain for multi-pose face recognition

Abstract

Abstract:This paper presents multipose faces recognition. The proposed scheme is based onholistic information of face image and small modification of classical LDA (modifiedLDA) classifier. The holistic information called as facial features is obtained by multiresolutionwavelet analysis. The modified LDA (MLDA) classifier that works based onmultivariate analysis classifies the facial features to a person’s class. The objectives ofthe proposed method are to create a compact and meaningful facial features withoutremoving significant face image information, to build a simple classification techniquewhich can well classify face images to a person’s class, to make the M-LDA-basedtraining system to solve the retraining problem of the PCA and LDA based recognitionsystem, to reduce the high memory space requirement of classical LDA and PCA, andto compare the effectiveness of proposed method to established LDA based recognitionsystems such as RLDA, DLDA, and SLDA. The result shows that the proposed methodgives good enough performance i.e. high enough success rate, short time processing,and small enough EER compare to establish LDA. In addition, the wavelet transforms isan efficient way for reducing the dimensional size of original image.