iccv iccv2013 iccv2013-261 iccv2013-261-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Wonjun Hwang, Kyungshik Roh, Junmo Kim
Abstract: We propose a novel unifying framework using a Markov network to learn the relationship between multiple classifiers in face recognition. We assume that we have several complementary classifiers and assign observation nodes to the features of a query image and hidden nodes to the features of gallery images. We connect each hidden node to its corresponding observation node and to the hidden nodes of other neighboring classifiers. For each observation-hidden node pair, we collect a set of gallery candidates that are most similar to the observation instance, and the relationship between the hidden nodes is captured in terms of the similarity matrix between the collected gallery images. Posterior probabilities in the hidden nodes are computed by the belief-propagation algorithm. The novelty of the proposed framework is the method that takes into account the classifier dependency using the results of each neighboring classifier. We present extensive results on two different evaluation protocols, known and unknown image variation tests, using three different databases, which shows that the proposed framework always leads to good accuracy in face recognition.
[1] E. Bailly-Bailliere, S. Bengio, F. Bimbot, M. Hamouz, J. Kittler, J. Mariethoz, J. Matas, K. Messer, V. Popovici, F. Poree, and et al. The banca database and evaluation protocol. Audio- and Video-based Biometric Person Authentication, 2688/2003, 2003. 4 11995588
[2] W. T. Freeman, E. C. Pasztor, and O. T. Carmichael. Learning low-level vision. International Journal of Computer Vision, 40(1):25–47, Jul. 2000. 2
[3] R. Huang, V. Pavlovic, and D. N. Metaxas. A hybrid face recognition method using markov random fields. International Conference on Pattern Recognition, 3: 157–160, Aug.
[4]
[5]
[6]
[7]
[8]
[9]
[10]
[11]
[12] 2004. 2, 3 W. Hwang, X. Huang, K. Noh, and J. Kim. Face recognition system using extended curvature gabor classifier bunch for low-resolution face image. IEEE CVPR Workshops, pages 15–22, Jun. 2011. 2, 5, 6 W. Hwang, H. Wang, H. Kim, S. Kee, and J. Kim. Face recognition system using multiple face model of hybrid fourier feature under uncontrolled illumination variation. IEEE Trans. on Image Processing, 20(4): 1152–1 165, Apr. 2011. 1 T. Kim, H. Kim, W. Hwang, S. Kee, and J. Lee. Componentbased LDA face descriptor for image retrieval. British Machine Vision Conference, pages 507–516, Sep. 2002. 1 J. Kittler, M. Hatef, R. P. Duin, and J. G. Matas. On combining classifiers. IEEE Trans. Pattern Analysis and Machine Intelligence, 3(20):226–239, Mar. 1998. 6 S. Z. Li and A. K. Jain. Handbook of Face Recognition. Springer, 2005. 1, 5 Z. Liu and C. Liu. Robust face recognition using color information. Advances in Biometrics, 5558/2009: 122–13 1, 2009. 1, 2 A. Martinez and A. Kak. PCA versus LDA. IEEE Trans. Pattern Recongition and Machine Intelligence, 23(2):228– 233, Feb. 2001. 1 K. McDonald and A. F. Smeaton. A comparison of score, rank and probability-based fusion methods for video shot retrieval. International Conference on Image and Video Retrieval, pages 61–70, 2005. 6 K. Messer, J. Kittler, M. Sadeghi, S. Marcel, C. Marcel, S. Bengio, F. Cardinaux, C. Sanderson, J. Czyz, L. Vandendorpe, and et al. Face verification competition on the xm2vts
[13]
[14]
[15]
[16]
[17]
[18]
[19]
[20] database. Audio- and Video-based Biometric Person Authentication, 2688/2003, 2003. 4 K. Nandakumar, Y. Chen, S. C. Dass, and A. K. Jain. Likelihood ratio based biometric score fusion. IEEE Trans. On Pattern Recognition and Machine Intelligence, 30(2):342– 347, Feb. 2008. 6 A. Pentland, B. Moghaddam, and T. Starner. View-based and modular eigenspaces for face recognition. Proc. IEEE, Computer Vision and Pattern Recognition, pages 84–91, Jun. 1994. 1 P. J. Phillips, P. J. Flynn, T. Scruggs, K. Bowyer, J. Chang, K. Hoffman, J. Marques, J. Min, and W. Worek. Overview of the face recognition grand challenge. Proc. IEEE, Computer Vision and Pattern Recognition, 1:947–954, San Diego, Jun. 2005. 4 S. Prabhakar and A. K. Jain. Decision-level fusion in fingerprint verification. Pattern Recognition, 4(35):861–874, Apr. 2002. 6 R. N. Rodrigues, G. N. Schroeder, J. J. Corso, and V. Govindaraju. Unconstrained face recognition using mrf priors and manifold traversing. International Conference on Biometrics: Theory, Applications and Systems, pages 1–6, Sep. 2009. 2 A. Ross and A. K. Jain. Information fusion in biometrics. Pattern Recognition Letters, 24:21 15–2125, Sept. 2003. 6 S. Shan, P. Yang, X. Chen, and W. Gao. Adaboost gabor fisher classifier for face recognition. Proceedings of International Workshop on Analysis and Modeling of Faces and Gestures, pages 278–291, 2005. 5, 6 Y. Su, S. Shan, X. Chen, and W. Gao. Hierarchical ensemble of global and local classifiers for face recognition. IEEE Trans. on Image Processing, 18(8): 1885–1896, August 2009. 2
[21] X. Tan and B. Triggs. Fusing gabor and lbp feature set for kernel-based face recognition. IEEE International Workshop on Analysis and Modeling of Face and Gestures, pages 235– 249, 2007. 1, 2
[22] X. Wang and X. Tang. Random sampling for subspace face recognition. International Journal of Computer Vision, 70:91–104, 2006. 5
[23] P. Yang, S. Shan, W. Gao, S. Z. Li, and D. Zhang. Face recognition using ada-boosted gabor features. Proc. IEEE, Automatic Face and Gesture Recognition, pages 356–361, May 2004. 5, 6 11995599