Improving FREAK Descriptor for Image Classification

  • Cristina Hilario GomezEmail author
  • Kartheek Medathati
  • Pierre Kornprobst
  • Vittorio Murino
  • Diego Sona
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9163)


In this paper we propose a new set of bio-inspired descriptors for image classification based on low-level processing performed by the retina. Taking as a starting point a descriptor called FREAK (Fast Retina Keypoint), we further extend it mimicking the center-surround organization of ganglion receptive fields. To test our approach we compared the performance of the original FREAK and our proposal on the 15 scene categories database. The results show that our approach outperforms the original FREAK for the scene classification task.


Bio-inspired descriptor Binary descriptor Center-surround ganglion cell organization FREAK Scene classification 



We thank M. San Biagio for his support in the image classification algorithm. This research received financial support from the 7th Framework Programme for Research of the European Commission, under Grant agreement num 600847: RENVISION project of the Future and Emerging Technologies (FET) programme Neuro-bio-inspired systems (NBIS) FET-Proactive Initiative.


  1. 1.
    Alahi, A., Ortiz, R., Vandergheynst, P.: FREAK: fast retina keypoint. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 510–517 (2012)Google Scholar
  2. 2.
    Bradski, G.: The opencv library. Dr. Dobb’s J. Softw. Tools 25, 120–126 (2000)Google Scholar
  3. 3.
    Chichilnisky, E.J.: A simple white noise analysis of neuronal light responses. Netw.: Comput. Neural Syst. 12(2), 199–213 (2001)zbMATHCrossRefGoogle Scholar
  4. 4.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2169–2178. IEEE Computer Society (2006)Google Scholar
  5. 5.
    Leutenegger, S., Chli, M., Siegwart, R.: Brisk: binary robust invariant scalable keypoints. In: ICCV 2011, pp. 2548–2555 (2011)Google Scholar
  6. 6.
    Meng, X., Wang, Z., Wu, L.: Building global image features for scene recognition. Pattern Recogn. 45(1), 373–380 (2012)CrossRefGoogle Scholar
  7. 7.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput. Vision 42(3), 145–175 (2001)zbMATHCrossRefGoogle Scholar
  8. 8.
    Oliva, A., Torralba, A.: Building the gist of a scene: the role of global image features in recognition. Prog. Brain Res. 155, 23–36 (2006)Google Scholar
  9. 9.
    Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 413–420 (2009)Google Scholar
  10. 10.
    Tola, E., Lepetit, V., Fua, P.: DAISY: an efficient dense descriptor applied to wide baseline stereo. IEEE Trans. Pattern Anal. Mach. Intell. 32(5), 815–830 (2010)CrossRefGoogle Scholar
  11. 11.
    Tuytelaars, T.: Dense interest points. In: The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, pp. 2281–2288, San Francisco, CA, USA, 13–18 June 2010 (2010)Google Scholar
  12. 12.
    Vedaldi, A., Fulkerson, B.: VLFeat: an open and portable library of computer vision algorithms (2008).
  13. 13.
    Vu, N.-S., Nguyen, T.P., Garcia, C.: Improving texture categorization with biologically inspired filtering. Image Vis. Comput. 32, 424–436 (2013)CrossRefGoogle Scholar
  14. 14.
    Wang, J., Wang, X., Yang, X., Zhao, A.: CS-FREAK: an improved binary descriptor. In: Tan, T., Ruan, Q., Wang, S., Ma, H., Huang, K. (eds.) IGTA 2014. CCIS, vol. 437, pp. 129–136. Springer, Heidelberg (2014) Google Scholar
  15. 15.
    Whiten, C., Laganiere, R., Bilodeau, G.A.: Efficient action recognition with MoFREAK. In: Proceedings of the 2013 International Conference on Computer and Robot Vision, pp. 319–325. IEEE Computer Society (2013)Google Scholar
  16. 16.
    Wohrer, A.: Model and large-scale simulator of a biological retina with contrast gain control. Ph.D. thesis, University of Nice Sophia-Antipolis (2008)Google Scholar
  17. 17.
    Wu, J., Rehg, J.M.: Centrist: a visual descriptor for scene categorization. IEEE Trans. Pattern Anal. Mach. Intell. 33(8), 1489–1501 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Cristina Hilario Gomez
    • 1
    Email author
  • Kartheek Medathati
    • 2
  • Pierre Kornprobst
    • 2
  • Vittorio Murino
    • 1
    • 3
  • Diego Sona
    • 1
  1. 1.Department of Pattern Analysis and Computer Vision, (PAVIS)Istituto Italiano di TecnologiaGenovaItaly
  2. 2.Neuromathcomp Project Team, INRIASophia AntipolisFrance
  3. 3.Department of Computer ScienceUniversity of VeronaVeronaItaly

Personalised recommendations