Research of Face Recognition System Based on TMS320DM642

Article Preview

Abstract:

This paper proposes an embedded face recognition system solution. The core of hardware architecture of the system is TMS320DM642 digital signal processor (DSP). The face recognition algorithm of the system mainly comprises improved face detection algorithm which is based on skin color, Gabor wavelet feature extraction algorithm, Principal Component Analysis (PCA) algorithm and nearest neighbor classifier algorithm. The results of testing on recognition efficiency and execution time show that the system can work stably and realize face recognition quickly and accurately.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

975-979

Citation:

Online since:

July 2013

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Li Li, Yuting Zhai. Application and the new trend of development about face recognition technology[J]. Blooming Season, 2012, (12): 407-408.

Google Scholar

[2] Zhiyan Zhao. Face Recognition System Based on DSP[D]. Henan University of Technology, Zhengzhou City, Henan Province: (2010).

Google Scholar

[3] Caikou Chen, Yixin Yu. A Fast Sparse Representation Based Classification[J]. Journal of Nanjing University, 2012, 48(1): 70-76.

Google Scholar

[4] Cui Xu, Ran Li. Face Detection of Gaussian Complexion Model based on the YCbCr Space[J]. Software Guide, 2009, 8(2): 179-181.

Google Scholar

[5] Otsu N. A Threshold Selection Method from Gray Level Histogram[J]. IEEE Trans. on Syst. Man, Cybern., 1979, 9(1): 62-66.

DOI: 10.1109/tsmc.1979.4310076

Google Scholar

[6] Jianxin Wu, Cuihua Li, Real-time Face Detection Based on Skin-color in Video Sequence[J]. Journal of Xiamen University, 2004, 43(3): 321-325.

Google Scholar

[7] MIT CBCL FaceDatabase. [Online]. Available: http: /cbcl. mit. edu/software-datasets/FaceData2. html.

Google Scholar