Face Recognition: The Problem of Compensating for Changes in Illumination Direction
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Kernel Eigenfaces vs. Kernel Fisherfaces: Face Recognition Using Kernel Methods
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Distance measures for PCA-based face recognition
Pattern Recognition Letters
Introduction to Data Mining, (First Edition)
Introduction to Data Mining, (First Edition)
Introduction to Genetic Algorithms
Introduction to Genetic Algorithms
Survey: Subspace methods for face recognition
Computer Science Review
Face recognition using the nearest feature line method
IEEE Transactions on Neural Networks
Hi-index | 0.01 |
Principal Component Analysis (PCA) turns out to be one of the most successful techniques in face recognition systems as a statistical method for dimensionality reduction. Even so, it is yet not optimal from the perspective of classification because the underlying distribution among different face classes in the image space is unpredicted and not known in advance. Besides, in practical applications, a question always raised on how much data should be included in the training. In this paper, a technique that associates genetic algorithm (GA) to PCA is proposed to maintain the property of PCA while enhancing the classification performance. It reconsiders the available training data and tries to find the best underlying distribution for classification. ORL, and Yale A databases have been used in the experiments to analyze and evaluate the performance of the proposed method compared to original PCA. The experiment results reveal that the proposed method outperforms PCA in terms of accuracy and classification time.