원문정보
초록
영어
Face Recognition is the most focused topic in the field of computer vision and pattern recognition. It has become a major thrust area for research in the last two decades due to the security aspects and demand for video. Face is focus of attention in the social intercourse and it plays a vital role in identification and recognition of individual emotions. Several facial recognition algorithms were developed and discussed in the literature but very little work is focused on facial recognition based on illumination. The appearance of the face image is usually affected by illumination conditions that hinder the facial recognition process. Hence in this paper, we propose and develop a new facial recognition algorithm based on Adaptive Haar Wavelet Transform called Tetrolet Transfrom. In Tetrolet transform, the determined orthonormal basis functions are adapted to geometrical features of the image follow a Truncated Gaussian Mixture Model (TGMM). The truncation on the feature vector has a significant influence in improving the recognition rate of the system.
목차
1. Introduction
2. Histogram Equalization
3. Adaptive Haar Wavelet Transform (Tetrolet Transform)
4. Literature of Guassian Mixture Model
5. Truncated Gaussian Mixture Model
6. Performance Evaluation
7. Conclusion
References