Comparison of Face Recognition Techniques
Byongjoo Oh · 한국정보기술학회논문지 · 2005
This paper presents a face recognition method and compares the performance of the presented technique with the PCA method. The presented method is based on the combination of well-known statistical representations of face images with the neural networks. They are Principal Component Analysis(PCA) with Multi-Layer Neural Networks(MLNN). The face images are first preprocessed by histogram equalization for contrast normalization. Then PCA technique is applied to reduce the dimension of the image and to produce the features of the face images. The features are then taken as the input of the Multi-Layer Neural Network. 'The classification is carried out by using MLNN. The proposed approaches has been tested on the ORL face database. The experimental results have been demonstrated, and the recognition rate of 95% has been achieved.