Advertisement

Best-Shot Selection for Video Face Recognition Using FPGA

  • Leonardo Chang
  • Ivis Rodés
  • Heydi Méndez
  • Ernesto del Toro
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5197)

Abstract

Video face recognition is widely used for security surveillance and other applications in which the information about faces is extracted and processed. One of the problems usually present in video face recognition is to determine in real time the suitable images for the good performance of the algorithms, taking into account that although computers keep getting faster, the amount of information to process is higher than the capacity of image processing algorithms available. In this work we propose a method that allows to obtain in real time the best image of each person present in the scene from a sequence of images, considering both image and face characteristics, and using FPGA technology to accelerate the image processing. With the proposed implementation of the method we managed to process 37 times more images per second, and 97% of the selected images proved to be adequate for face recognition.

Keywords

FPGA best-shot selection video face recognition 

References

  1. 1.
    Phillips, P.J., Scruggs, W.T., O’Toole, A.J., Flynn, P.J., Bowyer, K.W., Schott, C.L., Sharpe, M.: FRVT 2006 and ICE 2006: Large-Scale Results. NISTIR (2007)Google Scholar
  2. 2.
    Phillips, P.J., Grother, P.J., Micheals, R.J., Blackburn, D.M., TabassiI, E., Bone, J.M.: Face recognition vendor test 2002: Evaluation report. NISTIR (2003)Google Scholar
  3. 3.
    International Committee for Information Technologies and Standards: Face Recognition Format for Data Interchange. INCITS Secretariat, Information Technology Industry Council (2006)Google Scholar
  4. 4.
    DeHon, A.: The density advantage of configurable computing. IEE Computer 33(4), 41–49 (2000)CrossRefGoogle Scholar
  5. 5.
    Mühlbauer, F., Bobda, C.: A Dynamic Reconfigurable Hardware/Software Architecture for Object Tracking in Video Streams. EURASIP Journal on Embedded Systems 2006, 55–62 (2006)CrossRefGoogle Scholar
  6. 6.
    Gordon, G., Lewis, M.: Face Recognition Using Video Clips and Mug Shots. In: Proceedings of the Office of National Drug Control Policy (ONDCP), International Technical Symposium, Nashua, NH (1995)Google Scholar
  7. 7.
    Zhang, Y., Martinez, A.M.: From Stills to Video: Face Recognition Using a Probabilistic Approach. In: Computer Vision and Pattern Recognition Workshop, vol. 27(02), p. 78 (2004)Google Scholar
  8. 8.
    Yang, Z., Al, H., Wu, B., Lao, S., Cai, L.: Face Pose Estimation and its Application in Video Shot Selection. In: Proceedings of the 17th International Conference on Pattern Recognition, pp. 322–325 (2004)Google Scholar
  9. 9.
    Takuya, O., Lao, S.: Best-shot Selection from a Video Sequence of Face Images: An Implementation using Boosting Regression Algorithm. Omron Tech. 44(1), 17–20 (2004)Google Scholar
  10. 10.
    Shotaro, M., Kosuke, H., Shintaro, W., Hiroshi, K.: A Facial Expression-Oriented Best-Shot Face Recording System. Eizo Joho Media Gakkai Gijutsu Hokoku 29(74), 45–48 (2005)Google Scholar
  11. 11.
    Takacs, B.: Comparing face images using the modified Hausdorff distance. Pattern Recognition 31, 1873–1881 (1998)CrossRefGoogle Scholar
  12. 12.
    Draper, B.A., Beveridge, R., Willem, Böhm, A.P., Ross, C., Chawathe, M.: Accelerated image processing on fpgas. IEEE Transactions on Image Processing 12(12), 1543–1551 (2003)CrossRefGoogle Scholar
  13. 13.
    Torres, C., Arias, M.: FPGA-based Configurable Systolic Architecture for Window-based Image Processing. EURASIP Journal on Applied Signal Processing, Special Issue on Machine Perception on a Chip 2005(7), 1024–1034 (2005)CrossRefzbMATHGoogle Scholar
  14. 14.
    Chang, C., Hsiao, P., Huang, Z.: Integrated Operation of Image Capturing and Processing in FPGA. IJCSNS International Journal of Computer Science and Network Security 6(1), 173–180 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Leonardo Chang
    • 1
  • Ivis Rodés
    • 1
  • Heydi Méndez
    • 1
  • Ernesto del Toro
    • 2
  1. 1.Advanced Technologies Application CenterCuba
  2. 2.Microelectronics Research Center, CUJAECuba

Personalised recommendations