Skip to main content

Advertisement

SpringerLink
Log in

Accelerating Multiresolution Gabor Feature Extraction for Real Time Vision Applications

  • Published:
Journal of Signal Processing Systems Aims and scope Submit manuscript

Abstract

Multiresolution Gabor filter banks are used for feature extraction in a variety of applications as Gabor filters have shown to be exceptional feature extractors with a close correspondence to the simple cells in the primary visual cortex (V1) of the brain. Yet applying the Gabor filter is a computationally intensive task. Most applications that utilize the Gabor feature space require real time results; however, the large quantity of computations involved has hindered systems from achieving real time performance. The natural solution for such compute intensive tasks is parallelization. FPGAs have emerged as attractive platforms for compute intensive signal processing applications due to their massively parallel computation resources as well as low power consumption and affordability. We present a configurable architecture for Gabor feature extraction on FPGA that enhances the resource utilization of the FPGA hardware fabric while maintaining a streaming data flow to yield exceptional performance. The increased resource utilization resulting from configurability, optimizations, and resource sharing allows for higher levels of parallelism to achieve real time feature extraction of high resolution images. Two architectures are introduced. The first is an architecture for multiresolution feature extraction with extensive resource sharing for enhanced resource utilization. The second is an architecture for many-orientation applications using a coarse to fine grain method to enhance resource utilization by reducing the number of filters applied at different orientations. Our results show that our multiresolution implementation achieves real-time performance on 2048 × 1526 images and exhibits 6X speed up over a GPU implementation while exhibiting energy efficiency with 0.4fps/W compared to the GPU that achieves 0.036fps/W.[1] The implementation for many-orientation applications using the coarse to fine grain method exhibits resource saving of at most \( 2\sqrt{O} \)for O number of orientations and higher, compared to a fully parallel architecture and 25× speedup compared to a GPU implementation for 16 orientations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16

Similar content being viewed by others

References

  1. Cho, Y. C. P., Chandramoorthy, N., Irick, K. M., & Narayanan, V. (2012). Multiresolution Gabor Feature Extraction for Real Time Applications, in 2012 I.E. Workshop on Signal Processing Systems (pp. 55–60).

  2. Daugman, J. (1985). Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A, 2(7), 1160–1169.

    Article  Google Scholar 

  3. Messer, K., Kittler, J., Sadeghi, M., Hamouz, M., Kostin, A., Cardinaux, F., et al. (2004). Face authentication test on the BANCA database, in Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on, vol. 4, pp. 523–532.

  4. Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M., & Poggio, T. (2007). Robust object recognition with cortex-like mechanisms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(3), 411–426.

    Article  Google Scholar 

  5. Serre, T., Wolf, L., & Poggio, T. (2005). Object recognition with features inspired by visual cortex. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2, 994–1000.

    Google Scholar 

  6. Mutch, J., & Lowe, D. G. (2006). Multiclass object recognition with sparse, localized features. IEEE Computer Society Conference on Computer Vision Pattern and Recognition, 1, 11–18.

    Google Scholar 

  7. Yang, J., Liu, L., Jiang, T., & Fan, Y. (2003). A modified Gabor filter design method for fingerprint image enhancement. Pattern Recognition Letters, 24(12), 1805–1817.

    Article  Google Scholar 

  8. Yoshida Y., & Shioyama, T. (2002) Optimal gabor filters for high speed face identification, in Object recognition supported by user interaction for service robots, vol. 1, pp. 107–110.

  9. Serrano, Á., Martín de Diego, I., Conde, C., & Cabello, E. (2011). Analysis of variance of Gabor filter banks parameters for optimal face recognition. Pattern Recognition Letters, 32(15), 1998–2008.

    Article  Google Scholar 

  10. Zhang, T., & Lu, B. (2010) Selecting optimal orientations of gabor wavelet filters for facial image analysis, no. 60773090, pp. 218–227.

  11. Kong, A. (2008) An evaluation of Gabor orientation as a feature for face recognition, 2008 19th Int. Conf. Pattern Recognit., pp. 1–4, Dec. 2008.

  12. Painkras, E., & Charoensak, C. (2005) A VLSI architecture for Gabor filtering in face processing applications, 2005 Int. Symp. Intell. Signal Process. Commun. Syst. (pp. 437–440).

  13. Cook, J., Chandran, V., Sridharan, S., Fookes, C., Box, G. P. O, & Qld, B. (2005). Gabor Filter Bank Representation for 3D Face Recognition Queensland University of Technology 1 Introduction, no. Dicta.

  14. Laadjel, M., Bouridane, A., Kurugollu, F., & Yan, W. (2010). Palmprint recognition based on subspace analysis of Gabor filter bank. International Journal of Digital Crime and Forensics, 2(4), 1–15.

    Article  Google Scholar 

  15. Kong, W. K., Zhang, D., & Li, W. (2003). Palmprint feature extraction using 2-D Gabor filters. Pattern Recognition, 36(10), 2339–2347.

    Article  Google Scholar 

  16. Norouznezhad, E., Bigdeli, A., Postula, A., & Lovell, B. C. (2010). Object tracking on FPGA-based smart cameras using local oriented energy and phase features, Proc. Fourth ACM/IEEE Int. Conf. Distrib. Smart Cameras - ICDSC ’10, p. 33.

  17. Norouznezhad, E., Bigdeli, A., Postula, A., & Lovell, B. C. (2010). Robust object tracking using local oriented energy features and its hardware/software implementation, 2010 11th Int. Conf. Control Autom. Robot. Vis., pp. 2060–2066, Dec.

  18. Bianconi, F., & Fernández, A. (2007). Evaluation of the effects of Gabor filter parameters on texture classification. Pattern Recognition, 40(12), 3325–3335.

    Article  MATH  Google Scholar 

  19. Han, J., & Ma, K.-K. (2007). Rotation-invariant and scale-invariant Gabor features for texture image retrieval. Image and Vision Computing, 25(9), 1474–1481.

    Article  MathSciNet  Google Scholar 

  20. Rasmussen, C. (2005) Grouping dominant orientations for ill-structured road following, Proc. 2004 I.E. Comput. Soc. Conf. Comput. Vis. Pattern Recognition, 2004. CVPR 2004., vol. 1, pp. 470–477, 2004.

  21. Kong, H., Audibert, J.-Y., & Ponce, J. (2009). Vanishing point detection for road detection, 2009 I.E. Conf. Comput. Vis. Pattern Recognit., no. 3, pp. 96–103, Jun. 2009.

  22. Zhou, Y., & Zheng, Y.-P. (2009). Enhancement of muscle fibers in ultrasound images using Gabor filters,” in 2009 I.E. International Ultrasonics Symposium, 2009, pp. 2296–2299.

  23. Lecun, Y., Kavukcuoglu, K., Culurciello, E., Martini, B., Akselrod, P., Talay, S., et al. (2011) Large-Scale FPGA-based Convolutional Networks Chapter in Machine Learning on Very Large Data Sets , 2011, pp. 1–26.

  24. Chen, L., Lu, G., & Zhang, D. (2004). Effects of different Gabor filters parameters on image retrieval by texture, in 10th International Multimedia Modelling Conference, 2004. Proceedings., pp. 273–278.

  25. Munir, M. (2004). Fingerprint matching using gabor filters, Natl. Conf. Emerg. Technol., no. Figure 1, pp. 147–151, 2004.

  26. Turner, M. R. (1986). Texture discrimination by Gabor functions. Biological Cybernetics, 55(2–3), 71–82.

    Google Scholar 

  27. Manjunath, B. S., & Ma, W. Y. (1996). Texture features for browsing and retrieval of image data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8), 837–842.

    Article  Google Scholar 

  28. Marčelja, S. (1980). Mathematical description of the responses of simple cortical cells\ast. Journal of the Optical Society of America, 70(11), 1297–1300.

    Article  MathSciNet  Google Scholar 

  29. Moghaddam, H. A., Khajoie, T. T., Rouhi, A. H., & Tarzjan, M. S. (2005). Wavelet correlogram: a new approach for image indexing and retrieval. Pattern Recognition, 38(12), 2506–2518.

    Article  Google Scholar 

  30. Lades, M., Vorbruggen, J. C., Buhmann, J., Lange, J., von der Malsburg, C., Wurtz, R. P., & Konen, W. (1993). Distortion invariant object recognition in the dynamic link architecture. IEEE Transactions on Computers, 42(3), 300–311.

    Article  Google Scholar 

  31. Movellan, J. R. (2008). Tutorial on Gabor filters,

  32. Jun, W., & Asund, A. (2002). Strain contouring with Gabor filters: filter bank design. Applied Optics, 41(34), 7229.

    Article  Google Scholar 

  33. Gokberk, B., Irfanoglu, M. O., Akarun, L., & Alpaydm, E. Optimal Gabor kernel selection for face recognition,” in Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429), vol. 1, pp. I–677–80.

  34. Contassot-vivier, S., Lo Bosco, G., Nguyen, C. D. Lyon, E. N. S., & Grenoble, I. N. P. (2007). Multiresolution approach for image processing, Erasmus ICP-A-2007, pp. 1–9, 1996.

  35. Cho, Y. C. P., Bae, S., Jin, Y., Irick, K. M., & Narayanan, V. (2011). Exploring Gabor Filter Implementations for Visual Cortex Modeling on FPGA,” 2011 21st Int. Conf. F. Program. Log. Appl., no. 4, pp. 311–316, Sep. 2011.

  36. Areekul, V., Watchareeruetai, U., Suppasriwasuseth, K., & Tantaratana, S. (2005). Separable Gabor filter realization for fast fingerprint enhancement,” IEEE Int. Conf. Image Process. 2005, no. 2, pp. III–253, 2005.

  37. Amayeh G., & Tavakkoli, A. (2009). Accurate and efficient computation of gabor features in real-time applications,” Adv. Vis. Comput., 2009.

  38. Uzun, I. S., & Amira, A. (2005). Real-time 2-D wavelet transform implementation for HDTV compression. Real-Time Imaging, 11(2), 151–165.

    Article  Google Scholar 

  39. Voß, N. (2001) Design and implementation of an accelerated gabor filter bank using parallel hardware. Field-Programmable Logic and Applications,451–460.

  40. Nestares, O. (1998). Efficient spatial-domain implementation of a multiscale image representation based on Gabor functions. Journal of Electronic Imaging, 7(1), 166.

    Article  Google Scholar 

  41. Díaz, J., Ros, E., Mota, S., & Carrillo, R. (2007). Image processing architecture for local features computation, in Reconfigurable Computing: Architectures, Tools and Applications, vol. 4419, P. Diniz, E. Marques, K. Bertels, M. Fernandes, and J. Cardoso, Eds. Springer Berlin / Heidelberg, 2007, pp. 259–270.

  42. Xilinx, “Virtex-6 FPGA DSP48E1 Slice User Guide.” [Online]. Available: http://www.xilinx.com/support/documentation/user_guides/ug369.pdf.

  43. Altera, “Stratix V Device Handbook.” [Online]. Available: http://www.altera.com/literature/hb/stratix-v/stratix5_handbook.pdf.

  44. Pauwels, K., Tomasi, M., Diaz Alonso, J., Ros, E., & Van Hulle, M. M. (2011). A Comparison of FPGA and GPU for Real-Time Phase-based Optical Flow, Stereo, and Local Image Features,” IEEE Trans. Comput., no. January, 2011.

  45. Ilonen, J., & K. J., (2005) Efficient Computation of Gabor features.

Download references

Acknowledgments

This work was supported in part by NSF grants 0916887, 1147388, 1213052 and 0903432. Opinions expressed in this paper are solely of the authors.

This work was supported in part by the IT R&D program of MKE/KEIT [10035152, Energy Scalable Vector Processor - Primary Technology]

Author information

Authors and Affiliations

  1. Microsystems Design Laboratory, The Pennsylvania State University, State College, PA, USA

    Nandhini Chandramoorthy, Kevin M. Irick & Vijaykrishnan Narayanan

  2. Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea

    Yong Cheol Peter Cho

Authors
  1. Yong Cheol Peter Cho
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nandhini Chandramoorthy
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kevin M. Irick
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Vijaykrishnan Narayanan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yong Cheol Peter Cho.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cho, Y.C.P., Chandramoorthy, N., Irick, K.M. et al. Accelerating Multiresolution Gabor Feature Extraction for Real Time Vision Applications. J Sign Process Syst 76, 149–168 (2014). https://doi.org/10.1007/s11265-014-0873-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11265-014-0873-4

Keywords

Search

Navigation