A New Face Recognition System using Eigenfaces and Neural Network

H. Sahoolizadeh, Z. Heidari, and H. Dehghani (Iran)


Face recognition System, Principal Component Analysis, Linear Discriminant Analysis, Neural Network.


In this paper, a new face recognition system based on PCA (principal Component Analysis), LDA (Linear Discriminant Analysis) and neural network is introduced. This system consists of four steps: i) Preprocessing, ii) Dimension reduction using PCA, iii) LDA feature extraction and iv) classification using neural network. Combination of PCA and LDA is to improve the capability of LDA when a few samples of images are available and neural classifier is used to reduce number misclassification caused by not-linearly separable classes. The proposed system was tested on Yale face databases. Experimental results on this database demonstrated the effectiveness of the proposed system for face recognition with less misclassification in comparison with previous methods.

Important Links:

Go Back