Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection

Hong Pan, Søren Olsen, Yaping Zhu


Feature extraction and learning is critical for object recognition and detection. By embedding context cue of image attributes into the kernel descriptors, we propose a set of novel kernel descriptors called context kernel descriptors (CKD). The motivation of CKD is to use the spatial consistency of image attributes or features defined within a neighboring region to improve the robustness of descriptor matching in kernel space. For feature learning, we develop a novel codebook learning method, based on the Cauchy-Schwarz Quadratic Mutual Information (CSQMI) measure, to learn a compact and discriminative CKD codebook from a rich and redundant CKD dictionary. Projecting the original full-dimensional CKD onto the codebook, we reduce the dimensionality of CKD without losing its discriminability. CSQMI derived from Rényi quadratic entropy can be efficiently estimated using a Parzen window estimator even in high-dimensional space. In addition, the latent connection between Rényi quadratic entropy and the mapping data in kernel feature space further facilitates us to capture the geometric structure as well as the information about the underlying labels of the CKD using CSQMI. Thus the resulting codebook and reduced CKD are discriminative. We report superior performance of our algorithm for object recognition on benchmark datasets like Caltech-101 and CIFAR-10, as well as for detection on a challenging chicken feet dataset.


  1. Alcantarilla, P., Bartoli, A. and A.Davison. KAZE Features. Proc. of ECCV, 214-227, 2012.
  2. Alcantarilla, P., Nuevo, J., Bartoli, A., Fast explicit diffusion for accelerated features in nonlinear scale spaces. Proc. of BMVC, 13.1-13.11, 2013.
  3. Battiti, R., Using Mutual Information for Selecting Features in Supervised Neural Net Learning. IEEE Trans. Neural Networks, 5(4):537-550, 1994.
  4. Bay, H., Ess, A., Tuytelaars, T, Van Gool, L., SURF: Speeded Up Robust Features. Computer Vision and Image Understanding, 110(3):346-359, 2008.
  5. Bo, L., Lai, K., Ren, X., Fox, D., Object Recognition with Hierarchical Kernel Descriptors. Proc. of CVPR, 1:1729-1736, 2011.
  6. Bo, L., Ren, X., Fox, D., Kernel Descriptors for Visual Recognition. Proc. of NIPS, 244-252, 2010.
  7. Bo, L., Ren, X., Fox, D., Multipath sparse coding using hierarchical matching pursuit. Proc. of CVPR, 1:660- 667, 2013.
  8. Bo, L., Sminchisescu, C., Efficient Match Kernel between Sets of Features for Visual Recognition. Proc. of NIPS. 1:135-143, 2009.
  9. Bosch, A., Zisserman, A., and Munoz, X., Image Classification using Random Forests and Ferns. Proc. of ICCV, 1:1-8, 2007.
  10. Boureau, Y.-L., Roux, N. L., Bach, F., Ponce, J., LeCun, Y., Ask the locals: Multi-way local pooling for image recognition. Proc. of ICCV, 1:2651-2658, 2011.
  11. Brown, G., Pocock, A., Zhao, M., Luján, M., Conditional likelihood maximisation: a unifying framework for information theoretic feature selection. The Journal of Machine Learning Research, 13(1):27-66, 2012.
  12. Cao, Y., Wang, C., Li, Z., Zhang, L., Spatial -bag-offeatures. Proc. of CVPR, 1:3352-3359, 2010.
  13. Ciresan, D., Meier, U., Schmidhuber, J., Multi-column Deep Neural Networks for Image Classification. Proc. of CVPR, 3642-3649, 2012.
  14. Dalal, N., Triggs, B., Histograms of oriented gradients for human detection. Proc. of CVPR, 1:886 -893, 2005.
  15. Everingham, M. L, Van Gool, C., Williams, K. I., Winn, J., and Zisserman, A., The pascal visual object classes (VOC) challenge. International Journal of Computer Vision, 88(2): 303-338, 2010.
  16. Feng, J., Ni, B., Tian, Q., Yan, S., Geometric p-norm feature pooling for image classification. Proc. of CVPR, 1:2697-2704, 2011.
  17. Gómez-Chova, L., Jenssen, R., Camps-Valls, G., Kernel Entropy Component Analysis for Remote Sensing Image Clustering. IEEE Geoscience and Remote Sensing Letters, 9(2):312-316, 2012.
  18. Goodfellow, I., Courville, A., Bengio, Y., Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery, in NIPS Workshop on Challenges in Learning Hierarchical Models, 2011.
  19. Hellman, M.E., Raviv, J., Probability of error, equivocation, and the Chernoff bound. IEEE Trans. on Information Theory, 16:368-372, 1979.
  20. Hild II, K.E., Erdogmus, D., Principe, J.C., An Analysis of Entropy Estimators for Blind Source Separation. Signal Processing, 86(1):182-194, 2006.
  21. Hild II, K., Erdogmus, D., Torkkola, K., Principe, J., Feature Extraction Using Information-Theoretic Learning. IEEE Trans. Pattern Analysis and Machine Intelligence, 28(9):1385-1392, 2006.
  22. Jégou, H., Douze, M., Schmid, C., Packing bag-offeatures. Proc. of ICCV, 1:2357-2364, 2009.
  23. Jenssen, R., Kernel entropy component analysis. IEEE Trans. Pattern Analysis and Machine Intelligence, 32(5):847-860, 2010.
  24. Jenssen, R., Eltoft, T., A new information theoretic analysis of sum-of-squared-error kernel clustering. Neurocomputing, 72(1-3):23-31, 2008.
  25. Jia, Y., Huang, C., Darrell, T., Beyond spatial pyramids: Receptive field learning for pooled image features. Proc. of CVPR, 1:3370-3377, 2012.
  26. Jiang, Z., Zhang, G., and Davis, L. S., Submodular dictionary learning for sparse coding. Proc. of CVPR, 1:3418-3425, 2012.
  27. Kwak, N., Choi, C., Input Feature Selection by Mutual Information Based on Parzen Window. IEEE Trans. Pattern Analysis and Machine Intelligence, 24(12):1667-1671, 2002.
  28. Lazebnik, S., Schmid, C., Ponce, J., Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. Proc. of CVPR, 1:2169-2178, 2006.
  29. Le, Q., Ngiam, J., Chia, Z.C., Koh, P., Ng, A., Tiled convolutional neural networks. Proc. of NIPS, 1:1279- 1287, 2010.
  30. Leiva-Murillo, J., and Artes-Rodriguez, A., InformationTheoretic Linear Feature Extraction based on Kernel Density Estimators: A Review. IEEE Trans. Systems, Man, and Cybernetics, Part C: Applications and Reviews, 42(6):1180-1189, 2012.
  31. Li, F., Fergus, R., and Perona, P., One-shot learning of object categories. IEEE Trans. Pattern Analysis and Machine Intelligence, 28(4):594-611, 2006.
  32. Liu, C., Shum, H., Kullback-Leibler boosting. Proc. of CVPR, 1:587-594, 2003.
  33. Liu, L., Wang, L., and Liu, X., In defense of softassignment coding. Proc. of ICCV, 1:2486-2493, 2011.
  34. Lowe, D., Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2):91-110, 2004.
  35. McCann, S., Lowe, D., Spatially local coding for object recognition. Proc. of ACCV, 2012.
  36. Ojala, T., Pietikäinen, M., Mäenpää, T., Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Analysis and Machine Intelligence, 24(7):971-987, 2002.
  37. Oliveira, G., Nascimento, E., Vieira, A., Sparse spatial coding: a novel approach for efficient and accurate object recognition. Proc. of ICRA, 2592-2598, 2012.
  38. Parzen, E., On the estimation of a probability density function and the mode. Ann. Math. Statist., 33(3):1065-1076, 1962.
  39. Pedersen, K., Smidt, K., Ziem, A., Igel, C., Shape index descriptors applied to texture-based galaxy analysis. Proc. of ICCV, 1:2240-2447, 2013.
  40. Peng, H., Long F., Ding C., Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy. IEEE Trans. Pattern Analysis and Machine Intelligence, 27(8):1226-1238, 2005.
  41. Principe, J., Information theoretic learning: Renyi's entropy and kernel perspectives. Springer, 2010.
  42. Qiu, Q., Patel, V., Chellappa, R., Information-theoretic Dictionary Learning for Image Classification. IEEE Trans. Pattern Analysis and Machine Intelligence, April, 2014.
  43. Rényi, A., On measures of entropy and information. Fourth Berkeley Symposium on Mathematical Statistics and Probability, 547-561, 1961.
  44. Seidenari, L., Serra, G., Bagdanov, A., Del Bimbo, A., Local Pyramidal Descriptors for Image Recognition. IEEE Trans. Pattern Analysis and Machine Intelligence, 36(5):1033-1040, 2014.
  45. Torralba, A., Fergus, R., Freeman, W., 80 million tiny images: A large data set for nonparametric object and scene recognition. IEEE Trans. Pattern Analysis and Machine Intelligence, 30(11):1958-1970, 2008.
  46. Wang, P., Wang, J., Zeng, G., Xu, W., Zha, H., Li, S., Supervised Kernel Descriptor for Visual Recognition. Proc. of CVPR, 1:2858-2865, 2013.
  47. Yang, H., Moody, J., Feature Selection Based on Joint Mutual Information. Proc. of International ICSC Symposium on Advances in Intelligent Data Analysis, 1:22-25, 1999.
  48. Yu, K., Zhang, T., Improved local coordinate coding using local tangents. Proc. of ICML, 1:1215-1222, 2010.
  49. Zeiler, M., Fergus, R., Stochastic Pooling for Regularization of Deep Convolutional Neural Networks. Proc. of ICLR, 2013.
  50. Zeiler, M. D., Taylor, G. W., Fergus, R., Adaptive deconvolutional networks for mid and high level feature learning. Proc. of ICCV, 1:2018-2025, 2011.
  51. Zhang, Z., Hancock, E., A graph-based approach to feature selection. Graph-Based Representations in Pattern Recognition, 205-214, 2011.
  52. Zhong, Z., Hancock, E., Kernel entropy-based unsupervised spectral feature selection. International Journal of Pattern Recognition and Artificial Intelligence, 26(5):126002-1-18, 2012.

Paper Citation

in Harvard Style

Pan H., Olsen S. and Zhu Y. (2015). Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection . In Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-076-5, pages 99-109. DOI: 10.5220/0005212900990109

in Bibtex Style

author={Hong Pan and Søren Olsen and Yaping Zhu},
title={Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection},
booktitle={Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},

in EndNote Style

JO - Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection
SN - 978-989-758-076-5
AU - Pan H.
AU - Olsen S.
AU - Zhu Y.
PY - 2015
SP - 99
EP - 109
DO - 10.5220/0005212900990109