Block LDA and Gradient Image for Face Recognition

Authors:
Chuan-Yu Chang;Ching-Yu Hsieh
Affiliations:
Institute of Computer Science and Information Engineering, National Yunlin University of Science & Technology, Yunlin, Taiwan 64002;Institute of Computer Science and Information Engineering, National Yunlin University of Science & Technology, Yunlin, Taiwan 64002
Venue:
IEA/AIE '09 Proceedings of the 22nd International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems: Next-Generation Applied Intelligence
Year:
2009

Citing 9
Cited 0

Digital Image Processing

Digital Image Processing
Face Recognition: Features Versus Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
An improved face recognition technique based on modular PCA approach

Pattern Recognition Letters
Improved-LDA based face recognition using both facial global and local information

Pattern Recognition Letters
A face recognition system based on automatically determined facial fiducial points

Pattern Recognition
Elastic shape-texture matching for human face recognition

Pattern Recognition
Real-time face detection and recognition using hybrid-information extracted from face space and facial features

Image and Vision Computing
Face recognition using a fuzzy fisherface classifier

Pattern Recognition
Face recognition by independent component analysis

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Face recognition is an important issue in pattern recognition. Linear discriminant analysis (LDA) has been widely used in face recognition. However, the LDA-based face recognition methods usually encountered the small sample size (SSS) problem. The SSS problem occurs when the number of samples is far smaller than the dimensionality of the sample space. Therefore, this paper proposed a modified LDA (called block LDA) to divide the input image into several non-overlapping subimages of the same size, in order to increase the quantity of samples and reduce the dimensions of the sample space. In addition, to reduce the influence of illumination variations, face images were transferred to gradient image. Experimental results show that the proposed method indeed solves the SSS problem with a good recognition rate.