On a video surveillance system with a DSP by the LDA algorithm

Authors:
Jin Ok Kim;Jin Soo Kim;Chin Hyun Chung;Jun Hwang
Affiliations:
Faculty of Multimedia, Daegu Haany University, Gyeongsangbuk-do, Korea;Department of Information and Control Engineering, Kwangwoon University, Seoul, Korea;Department of Information and Control Engineering, Kwangwoon University, Seoul, Korea;Division of Information and Communication Eng., Seoul Women's University, Seoul, Korea
Venue:
HSI'05 Proceedings of the 3rd international conference on Human Society@Internet: web and Communication Technologies and Internet-Related Social Issues
Year:
2005

Citing 6
Cited 0

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Frontal-view face detection and facial feature extraction using color, shape and symmetry based cost functions

Pattern Recognition Letters
A Fast and Accurate Face Detector Based on Neural Networks

IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Processing: PIKS Inside

Digital Image Processing: PIKS Inside
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
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)

Quantified Score

Hi-index	0.00

Visualization

Abstract

As face recognition algorithms move from research labs to real world product, power consumption and cost become critical issues, and DSP-based implementations become more attractive. Also, “real-time” automatic personal identification system should meet the conflicting dual requirements of accuracy and response time. In addition, it also should be user-friendly. This paper proposes a method of face recognition by the LDA Algorithm with the facial feature extracted by chrominance component in color images. We designed a face recognition system based on a DSP. At first, we apply a lighting compensation algorithm with contrast-limited adaptive histogram equalization to the input image according to the variation of light condition. While we project the face image from the original vector space to a face subspace via PCA , we use the LDA to obtain the best linear classifier. The experimental results with real-time input video show that the algorithm has a pretty good performance on a DSP-based face recognition system. And then, we estimate the Euclidian distances between the input image's feature vector and trained image's feature vector.