Real-Time Implementation of Face Recognition Algorithms on DSP Chip
This paper describes a prototype implementation of face recognition and verification algorithms in a stand-alone system using the TI TMS320C6711 chip. This system is organized to capture an image sequence, find the features of face in the images, and recognize and verify a person. The current implementation uses the methods of PCA(Principal Component Analysis) and SVM(Support Vector Machines). We have made several tests on video data, and measured the performance and the speed of the proposed system in real environment. Finally, the result has confirmed us that the proposed system can be applied to various applications which are impossible in conventional PC-based systems.
KeywordsSupport Vector Machine Face Recognition Face Image Face Detection Training Stage
Unable to display preview. Download preview PDF.
- Scholkopf, B., Burges, C., Smola, A.: Advances in Kernel Methods-Support Vector Learning. MIT Press (1998)Google Scholar
- Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines. Cambridge University Press (2000)Google Scholar
- IBM ZISC036 Data Sheet, http://www.ibm.com
- Yang, F., Paindavoine, M., Abdi, H.: Parallel Implementation on DSPs of a Face Detection Algorithm. Proc. of International Conference on the Software Process, Chicago, USA (1998)Google Scholar
- Gilbert, J. M., Yang, W.: A Real-Time Face Recognition System Using Custom VLSI Hardware. Proc. of Computer Architectures for Machine Perceptron Workshop, New Orleans, USA (1993) 58–66Google Scholar
- Texas Instruments: TMS320C6000 Tools: Vector Table and Boot ROM Creation (Rev. C). Application Report SPRA544C (2002)Google Scholar