Advertisement

Journal of Real-Time Image Processing

, Volume 2, Issue 4, pp 249–258 | Cite as

An FPGA-based accelerator for Fourier Descriptors computing for color object recognition using SVM

  • Fethi Smach
  • Johel Miteran
  • Mohamed Atri
  • Julien Dubois
  • Mohamed Abid
  • Jean-Paul Gauthier
Special Issue

Abstract

Fourier Descriptors (FD) can be used as feature vector components in various applications, such as real-time color object recognition or image retrieval. The full process is composed of the feature extraction followed by a classification step performed using support vector machine (SVM). In order to accelerate the computation of FD, a hardware implementation using FPGA technology is presented in this paper. We evaluated classification performance with respect to lighting variations and noise sensibility. Several experiments were carried out on three databases. Then an efficient architecture for FD computation on FPGAs is proposed and designed as accelerator. The WildCard is used to prototype this implementation. This design can have an operation speed up of approximately 10 compared to the standard software PC implementation.

Keywords

Fourier Descriptors Color object recognition Field programmable gate array (FPGA) SVM 

References

  1. 1.
    Reyna Rojas, R., Houzet, R., Albenge, M.F., Esteve, D.: Implementation of the SVM neural network generalization function of for image processing. International Workshop on Computer Architecture for Machine Perception (CAMP’2000), Padova, Italy, 11–13 September 2000, pp. 147–151Google Scholar
  2. 2.
    Zhu, J., Sutton, P.: FPGA implementation of neural networks: “a survey of a decade of progress”, In: Proceedings of the 13th International Conference on Field Programmable Logic and Applications (FPL 2003), Lisbon, Portugal, 2003, pp. 1062–1066Google Scholar
  3. 3.
    Yang, F., Paindavoine, M.: Implementation of a RBF neural network on embedded systems: real time face tracking and identity verification. IEEE Trans. Neural Netw. 14(5), 1162–1175 (2003)CrossRefGoogle Scholar
  4. 4.
    Vapnik, V.: The nature of statistical learning theory. Springer, New York (1995)zbMATHGoogle Scholar
  5. 5.
    Raj Bahadur, Y., Naveen Nishchal, K., Arun Gupta, K., Vinod Rastogi, K.: Retrieval and classification of shape-based objects using Fourier, generic Fourier, and wavelet Fourier Descriptors technique: a comparative study. Opt. Lasers Eng. 45, 695–708 (2007)CrossRefGoogle Scholar
  6. 6.
    Javier Diaz, F., Buron, A.M., Solana, J.M.: Haar wavelet based processor scheme for image coding with low circuit complexity. Comput. Electrical Eng. 33, 109–126 (2007)CrossRefzbMATHGoogle Scholar
  7. 7.
    Gauthier, J.P., Bornard, G., Silbermann, M.: Harmonic analysis on motions groups and their homogenous spaces. IEEE Trans. Syst. Man Cybern. 21, 159–172 (1991)CrossRefMathSciNetzbMATHGoogle Scholar
  8. 8.
    Fonga, H.: Analyse harmonique sur les groupes et reconnaissance de formes. PhD thesis, université de Grenoble (1992)Google Scholar
  9. 9.
    Smach, F., Lemaitre, C., Mitéran, J., Gauthier, J.P., Abid, M.: Colour object recognition combining motion descriptors, zernike moments and support vector. In: Proceeding of IECON’06, IEEE, Paris-CNAM, France, 2006, pp. 3238–3242Google Scholar
  10. 10.
    Crookes, D., Benkrid, K., Bouridane, A., Alotaibi, K., Benkrid, A.: Design and implementation of a high level programming environment for FPGA-based image processing. IEE Proc. Vis. Image Signal Process. 147(4), 377–384 (2000)CrossRefGoogle Scholar
  11. 11.
    Tahir, M.A., Bouridane, A., Kurugoullu, F.: An FPGA based coprocessor for GLCM and Haralick texture features and their application in prostate cancer classification. Analog Integr. Circuit Signal Process. 35, 205–215 (2005)CrossRefGoogle Scholar
  12. 12.
    Nguyen, D., Halupka, D., Aarabi, P., Sheikholeslami, A.: Real-time face detection, lip feature extraction using field programmable gate arrays. IEEE Trans. Syst. Man Cybern. B Cybern. 36(4), 902–912 (2006)CrossRefGoogle Scholar
  13. 13.
    Mukherjee, R., Jones, A., Banerjee, P.: System level synthesis of multiple ip blocks in the behavioral synthesis tool. International Conference on Parallel and Distributed Computing and Systems (PDCS), 2003Google Scholar
  14. 14.
    Guo, Z., Mitra, A., Najjar, W.: Automation of IP core interface general for reconfigurable computing. 16th International Conference on Field programmable Logic Applications (FPL 2006) Madrid, Spain, 2006Google Scholar
  15. 15.
    Mitéran J., Bouillant, S., Bourennane, E.: SVM approximation for real-time image segmentation by using an improved hyperrectangles-based method, real time imaging. Elsevier 9(3), 179–188 (2003)Google Scholar
  16. 16.
    Niyogi, P., Burges, C., Ramesh, P.: Distinctive feature detection using support vector machines. ICASSP 99, 425–428 (1999)Google Scholar
  17. 17.
    Schölkopf, B., Smola, A., Müller, K.-R., Burges, C.J.C., Vapnik, V.: Support vector methods in learning and feature extraction. Aust. J. Intell. Inf. Process. Syst. 1, 3–9 (1998)Google Scholar
  18. 18.
  19. 19.
    Hjelmas, E.: Face detection: a survey. Comput Vis Image Underst 83(3), 236–274 (2001). http://www.ingentaconnect.com/content/els/10773142/2001/00000083/00000003/art90921 Google Scholar
  20. 20.
    Huang, R., Pavlovic, V., Metxas, D.N.: A hybrid face recognition method using Markov random field’s. In: Proceeding of ICPR, 2004, pp. 157–160Google Scholar
  21. 21.
    ORL face database, AT&T Laboratories, Cambridge, U.K. http://www.cam-orl.co.uk/facedatabase.html
  22. 22.
    Martinez, A.M.: Recognition of partially occluded and/or imprecisely localized faces using probabilistic approach. In: Proceeding of IEEE Computer Vision and Pattern Recognition, CVPR’2000, pp. 712–717Google Scholar
  23. 23.
    Khotanzad, A., Yaw, H.H.: Invariant image recognition by Zernike moments. IEEE Trans. PAMI 12(5), 489–497 (1990)Google Scholar
  24. 24.
    Obrzalek, S., Matas, J.: Object recognition using local affine frames on distinguished regions. In: Electronic Proceeding of the 13th British Machine Vision Conference, University of Cardiff, 2002, pp. 113–122Google Scholar
  25. 25.
    Guo, G.D., Li, S., Chan, K.: Face recognition by support vector machines. In: Proceedings of International Conference on Automatic Face and Gesture Recognition, 2000, pp. 196–201Google Scholar
  26. 26.
    Yifeng, Q., Badawy, W.: Tutorial on an Integrated Virtual Socket Hardware-Accelerated Co-design Platform for MPEG4-Part9 ISO/IEC JTC1/SC29/WG11 M12789, Bangkok, Thailand, January 2006, pp. 3–28Google Scholar
  27. 27.
    Schumacher, P., Mattavelli, M., Chirila-Rus, A., Turney, R.: A virtual socket framework for rapid emulation of video and multimedia designs. In: Multimedia and Expo, ICME 2005, 6–8 July 2005, pp. 872–875Google Scholar
  28. 28.
    Annapolis Microsystems Inc., Annapolis WILDCARD System Reference Manual, Revision 2.6. http://www.annapmicro.com (2003)
  29. 29.
    Dubois, J., Mattavelli, M., Pierrefeu, L., Mitéran, J.: Configurable motion-estimation hardware accelerator module for the MPEG-4 reference hardware description platform. In: Proceeding of IEEE International Conference on Image processing (ICIP), vol. 3, Genova, 11–14 September, 2005, pp. 1040–1043Google Scholar
  30. 30.
    Kinane, A., Muresan, V., O’Connor, N.E., Murphy, N., Marlow, S.: Energy-efficient hardware architecture for variable N-point 1D DCT. In: Proceeding of PATMOS, 2004, pp. 780–788Google Scholar

Copyright information

© Springer-Verlag 2007

Authors and Affiliations

  • Fethi Smach
    • 1
    • 2
  • Johel Miteran
    • 1
  • Mohamed Atri
    • 3
  • Julien Dubois
    • 1
  • Mohamed Abid
    • 2
  • Jean-Paul Gauthier
    • 1
  1. 1.Le2i Faculté Mirande Aile H. Université de BourgogneDijonFrance
  2. 2.Laboratoire CESENISSfaxTunisia
  3. 3.Laboratoire EμE, FSMMonastirTunisia

Personalised recommendations