KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Bio-Inspired Object Recognition Using Parameterized Metric Learning

  • Li, Xiong (Department of Automation, Shanghai Jiao Tong University) ;
  • Wang, Bin (Department of Automation, Shanghai Jiao Tong University) ;
  • Liu, Yuncai (Department of Automation, Shanghai Jiao Tong University)
  • Received : 2012.12.11
  • Accepted : 2013.03.19
  • Published : 2013.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Computing global features based on local features using a bio-inspired framework has shown promising performance. However, for some tough applications with large intra-class variances, a single local feature is inadequate to represent all the attributes of the images. To integrate the complementary abilities of multiple local features, in this paper we have extended the efficacy of the bio-inspired framework, HMAX, to adapt heterogeneous features for global feature extraction. Given multiple global features, we propose an approach, designated as parameterized metric learning, for high dimensional feature fusion. The fusion parameters are solved by maximizing the canonical correlation with respect to the parameters. Experimental results show that our method achieves significant improvements over the benchmark bio-inspired framework, HMAX, and other related methods on the Caltech dataset, under varying numbers of training samples and feature elements.

Keywords

References

  1. X. Li, X. Zhao, Y. Fu, and Y. Liu, "Weak metric learning for feature fusion towards perception-inspired object recognition," in Proc. of International Conference on MultiMedia Modeling, pp. 273-283, 2010.
  2. M. Riesenhuber and T. Poggio, "Hierarchical models of object recognition in cortex," Nature Neuroscience, vol. 2, pp. 1019-1025, 1999. https://doi.org/10.1038/14819
  3. T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, and T. Poggio, "Robust object recognition with cortex-like mechanisms," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 3, pp. 411-426, 2007. https://doi.org/10.1109/TPAMI.2007.56
  4. A. Frome, Y. Singer, and J. Malik, "Image retrieval and classification using local distance functions," NIPS, 2007.
  5. J. Mutch and D. Lowe, "Object class recognition and localization using sparse features with limited receptive fields," International Journal of Computer Vision, vol. 80, no. 1, pp. 45-57, 2008. https://doi.org/10.1007/s11263-007-0118-0
  6. N. Pinto and D. Cox, "High-throughput-derived biologically-inspired features for unconstrained face recognition," Image and Vision Computing, vol. 30, no. 3, pp. 159-168, 2012. https://doi.org/10.1016/j.imavis.2011.12.009
  7. K. Rajaei, S. Khaligh-Razavi, M. Ghodrati, R. Ebrahimpour, and M.E.S.A Abadi, "A stable biologically motivated learning mechanism for visual feature extraction to handle facial categorization," PLOS one, vol. 7, 2012.
  8. A.A. Maashri, M. Debole, M. Cotter, N. Chandramoorthy, Y. Xiao, V. Narayanan, and C. Chakrabarti, "Accelerating neuromorphic vision algorithms for recognition," in Proc. of Annual Design Automation Conference, 2012.
  9. J.Z. Leibo, J. Mutch and T. Poggio, "Why the brain separates face recognition from object recognition," NIPS, 2011.
  10. B. Timothy, T. Konkle, A. George and A. Oliva, "Real-world objects are not represented as bound units: independent forgetting of different object details from visual memory," Journal of Experimental Psychology, 2012.
  11. E. Rosch, "Natural Categories," Cognitive Psychology, vol. 4, no. 3, pp. 328-350, 1973. https://doi.org/10.1016/0010-0285(73)90017-0
  12. D. Lowe, "Object recognition from local scale-invariant features," ICCV, pp. 1150-1157, 1999.
  13. Y. Fu, L. Cao, G. Guo and T. S. Huang, "Multiple feature fusion by subspace learning," CIVR, pp. 127-134, 2008.
  14. Y. Lin, T. Liu and C. Fuh, "Dimensionality Reduction for Data in Multiple Feature Representations," NIPS, 2009.
  15. H. Zhang, A. Berg, M. Maire and J. Malik, "SVM-KNN: Discriminative nearest neighbor classification for visual category recognition," CVPR, 2006.
  16. P. Lai and C. Fyfe, "Kernel and nonlinear canonical correlation analysis," International Journal of Neural Systems, vol. 10, no. 5, pp. 365-378, 2000. https://doi.org/10.1142/S012906570000034X
  17. D. Hardoon, S. Szedmak and J. Shawe-Taylor, "Canonical correlation analysis: an overview with application to learning methods," Neural Computation, vol. 16, no. 12, pp. 2639-2664, 2004. https://doi.org/10.1162/0899766042321814
  18. T. Serre, A. Oliva and T. Poggio, "A feedforward architecture accounts for rapid categorization," in Proc. of the National Academy of Science, vol. 104, no. 15, pp. 6424-6429, 2007. https://doi.org/10.1073/pnas.0700622104
  19. M. Schultz and T. Joachims, "Learning a distance metric from relative comparisons," NIPS, 2004.
  20. S. Belongie, J. Malik and J. Puzicha, "Shape matching and object recognition using shape contexts," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 509-522, 2002.
  21. A. Berg and J. Malik, "Geometric blur and template matching," CVPR, 2001.
  22. T. Lindeberg and Scale-space, "A framework for handling image structures at multiple scales," European Organization for Nuclear Research-Reports-CERN, pp. 27-38, 1996.
  23. T. Kim, J. Kittler and R. Cipolla, "Discriminative learning and recognition of image set classes using canonical correlations," IEEE Transactions on Pattern Analysis and Ma-chine Intelligence, vol. 29, no. 6, pp. 1005-1018, 2007. https://doi.org/10.1109/TPAMI.2007.1037
  24. Q. Sun, S. Zeng, Y. Liu, P. Heng and D. Xia, "A new method of feature fusion and its application in image recognition," Pattern Recognition, vol. 38, no. 12, pp. 2437-2448, 2005. https://doi.org/10.1016/j.patcog.2004.12.013
  25. S. Karayev, M. Fritz, S. Fidler and T. Darrell, "A probabilistic model for recursive factorized image features," CVPR, 2011.
  26. J. Matas, O. Chum, M. Urban and T. Pajdla, "Robust wide-baseline stereo from maximal-ly stable extremal regions," Image and Vision Computing, vol. 22, no. 10, pp. 761-767, 2004. https://doi.org/10.1016/j.imavis.2004.02.006
  27. K. Mikolajczyk and C. Schmid, "An affine invariant interest point detector," ECCV, pp. 128-142, 2002.
  28. K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir and L. Gool, "A comparison of affine region detectors," International Journal of Computer Vision, vol. 65, no. 1, pp. 43-72, 2005. https://doi.org/10.1007/s11263-005-3848-x
  29. N. Pinto, http://mkl.ucsd.edu/dataset/ucsd-mit-caltech-101-mkl-dataset.
  30. C. Chang and C. Lin, "LIBSVM: A library for support vector machines," ACM Transactions on Intelligent Systems and Technology, vol. 2, no. 3, pp. 1-27, 2011.