JSTS:Journal of Semiconductor Technology and Science

  • 제12권2호
  • /
  • Pages.162-167
  • /
  • 2012
  • /
  • 1598-1657(pISSN)
  • /
  • 2233-4866(eISSN)
대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지
DOI QR코드

DOI QR Code

Design of High-Performance Unified Circuit for Linear and Non-Linear SVM Classifications

  • Kim, Soo-Jin (Dep. Electronics and Information Engineering, Hankuk University of Foreign Studies) ;
  • Lee, Seon-Young (Dep. Electronics and Information Engineering, Hankuk University of Foreign Studies) ;
  • Cho, Kyeong-Soon (Dep. Electronics and Information Engineering, Hankuk University of Foreign Studies)
  • 투고 : 2011.08.29
  • 발행 : 2012.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This paper describes the design of a high-performance unified SVM classifier circuit. The proposed circuit supports both linear and non-linear SVM classifications. In order to ensure efficient classification, a 48x96 or 64x64 sliding window with 20 window strides is used. We reduced the circuit size by sharing most of the resources required for both types of classification. We described the proposed unified SVM classifier circuit using the Verilog HDL and synthesized the gate-level circuit using 65nm standard cell library. The synthesized circuit consists of 661,261 gates, operates at the maximum operating frequency of 152 MHz and processes up to 33.8 640x480 image frames per second.

키워드

참고문헌

  1. Vapnik, V. N., Statistical Learning Theory, John Wiley & Sons, 1998.
  2. Gomes Filho, J., Raffo, M., Strum, M., and Wan Jiang Chau, "A General-purpose Dynamically Reconfigulable SVM," 2010 VI Southern Programmable Logic Conference, pp.107-112, Mar., 2010.
  3. Papadonikolakis, M. and Bougamis, C., "A Novel FPGA-based SVM Classifier," Fieldprogrammable Technology, IEEE International conference on, pp.283-286, Dec., 2010.
  4. Kyrkou, C. and Theocharides, T., "Scope: Towards a Systolic Array for SVM Object Detection," IEEE Embedded Systems Letters, Vol. 1, No. 2, pp.46-49, Aug., 2009. https://doi.org/10.1109/LES.2009.2034709
  5. Demir, B. and Erturk, S., "Improving SVM Classification Accuracy using a Hierarchical Approach for Hyperspectal Images," Image Processing, IEEE International Conference on, pp.2849-2852, Nov., 2009.
  6. Hsu, C. F., Mong-Kai Ku, and Li Yen Liu, "Support Vector Machine FPGA Implemantation for Video Shot Boundary Detection Application," IEEE International SoC Conference, pp.239-242, Sep., 2009.
  7. Ruiz-Llata, M., Guarnizo, G., and Yebenes-Calvino. M, "FPGA Implementation of a Support Vector Machine for Classification and Regression," Neural Networks, International Joint Conference on, pp.1- 5, Jul., 2010.
  8. Irick, K., DeBole, M., Narayanan, V., and Gayasen, A., "A Hardware Efficient Support Vector Machine Architecture for FPGA," Field-programmable Custom Computing Machines, International Symposium on, pp.304-305, Apr., 2008.
  9. Manikandan, J. and Venkataramani, B., "Design of a Modified One-against-all SVM Classifier," Systems, Man, and Cybernetics, IEEE International Conference on, pp.1869-1874, Oct., 2009.
  10. Kyrkou, C. and Theocharides, T., "A Parallel Hardware Architecture for Real-time Object Detection with Support Vector Machines," Computers , IEEE Transactions on, pp.1-12, 2011.
  11. Omar, P., Raquel, V., and Oscar. Y, "An FPGA Implementation of Linear Kernel Support Vector Machines," Reconfigurable Computing and FPGA's, IEEE International Conference on, pp.1-6, Sep., 2006.
  12. Reyna, R. A., Esteve, D., Houzet, D., and Albenge, M. F., "Implementation of the SVM Neural Network Generalization Function for Image Processing," Computer Architectures for Machine Perception, Proceedings of IEEE International Workshop on, pp.147-151, Sep., 2000.
  13. Dalal, N. and Triggs, B., "Histograms of Oriented Gradients for Human Detection," Computer Vision and Patttern Recognition, IEEE Computer Society Conference on, Vol. 1, pp.886-893, Jun., 2005.
  14. Tang, P. T. P., "Table-driven Implemantation of the Exponential Function in IEEE Floating-point Arithmetic," Mathematical Software, ACM Trans. on, Vol. 16, No. 2, pp.144-157, Jun., 1989.