On a Video Surveillance System with a DSP by the LDA Algorithm
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.
KeywordsFace Recognition Linear Discriminant Analysis Face Detection Skin Tone Video Surveillance System
Unable to display preview. Download preview PDF.
- 2.Yang, M.H.: Kernel eigenfaces vs. kernel fisherfaces: face recognition using kernel method. In: Automatic Face and Gesture Recognition, 2002. Proceedings. 4th IEEE International Conference, pp. 208–213 (2002)Google Scholar
- 4.Moritz, S.: Computer Vision and Human Skin Colour. PhD thesis, Electrical Engineering, Technical University of Berlin, Germany (2004)Google Scholar
- 5.Vezhnevets, V., Sazonov, V., Andreeva, A.: A survey on pixel-based skin color detection techniques. GraphiCon, Moscow (2003)Google Scholar
- 6.Phillips, P.J., McCabe, R.M., Chellappa, R.: Biometric image processing and recognition. In: Proceedings, European Signal Processing Conference (1998)Google Scholar
- 7.Texas Instrument: TMS320C6000 Imaging Developer’s Kit programmer’s Guide (2001)Google Scholar
- 8.Menser, B., Brunig, M.: Locating human faces in color images with complex background. Intelligent Signal Processing and Comm. Systems, 533–536 (1999)Google Scholar
- 10.IMDB. Intelligent Multimedia Laboratory, Postech, Korea (2001)Google Scholar
- 11.Mathworks: Image Processing Toolbox User’s Guide. The MathWorks (2002)Google Scholar
- 12.Belnumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Trans. on PAMI (1997)Google Scholar