Similar articles

Abstract: Object representation based on local features is a topical subject in the domain of image understanding and computer vision. We discuss the defects of global features in present methods and the advantages of local features in object recognition, and briefly explore state-of-the-art recognition methods using local features, especially the main approaches of local feature extraction and object representation. To clearly explain these methods, the problem of local feature extraction is divided into feature region detection, feature region description, and feature space optimization. The main components and merits of these steps are presented. Technologies for object presentation are classified into three types: vector space, sliding window, and structure relationship models. Future development trends are discussed briefly.

[1]Agarwal, S., Awan, A., Roth, D., 2004. Learning to detect objects in images via a sparse, part-based representation. IEEE Trans. Pattern Anal. Mach. Intell., 26(11):1475-1490.

[2]Baumberg, A., 2000. Reliable Feature Matching across Widely Separated Views. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.774-781.

[3]Bay, H., Ess, A., Tuytelaars, T., Gool, L.V., 2008. SURF: speeded up robust features. Comput. Vis. Image Understand., 110(3):346-359.

[4]Belongie, S., Malik, J., Puchiza, J., 2002. Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Anal. Mach. Intell., 24(4):509-522.

[5]Berg, A.C., Berg, T.L., Malik, J., 2005. Shape Matching and Object Recognition Using Low Distortion Correspondences. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.26-33.

[6]Bilen, H., Namboodiri, V.P., van Gool, L.J., 2012. Classification with global, local and shared features. LNCS, 7476:134-143.

[7]Cao, J., Chen, H.Q., Zhang, K., Niu, C.F., 2011a. Moving cast shadow detection based on region color and texture. Robot, 33(5):628-633 (in Chinese).

[8]Cao, J., Liu, Q.X., Gao, C.X., Liu, Y.S., 2011b. Object recognition with corner-based feature. Trans. Beijing Inst. Technol., 31(3):308-312 (in Chinese).

[9]Cao, J., Chen, H.Q., Mao, M.Y., 2011c. Optimization Algorithms for Local Features. Int. Conf. on Automation, Communication, Architectonics and Materials, p.921-924.

[10]Chen, G.Y., Gleason, S., 2012. Ridgelet Moment Invariants for Pattern Recognition. Proc. 25th IEEE Canadian Conf. on Electrical & Computer Engineering, p.1-4.

[11]Chen, Q., Song, Z., Hua, Y., Huang, Z.Y., Yan, S.C., 2012. Hierarchical Matching with Side Information for Image Classification. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.3426-3433.

[12]Chia, A.Y., Rajan, D., Leung, M.K., Rahardja, S., 2012. Object recognition by discriminative combinations of line segments, ellipses, and appearance features. IEEE Trans. Pattern Anal. Mach. Intell. 34(9):1758-1772.

[13]Choi, J.Y., Ro, Y.M., Plataniotis, K.N., 2012. Color local texture features for color face recognition. IEEE Trans. Image Process., 21(3):1366-1380.

[14]Cristianini, N., Shawe-Taylor, J., Lodhi, H., 2002. Latent semantic kernels. J. Intell. Inf. Syst., 18(2/3):127-152.

[15]Dai, D.Q., Yuen, P.C., 2003. Regularized discriminant analysis and its application to face recognition. Pattern Recogn., 36(3):845-847.

[16]Dalal, N., Triggs, B., 2005. Histograms of Oriented Gradients for Human Detection. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.886-893.

[17]Ding, H., Li, X.D., Zhao, H.J., Xiao, W., 2012. A New Generalized Affine Moment Invariants for Shape Retrieval and Object Recognition. Proc. IEEE Int. Symp. on Instrumentation and Control Technology, p.137-142.

[18]Fergus, R., Perona, P., Zisserman, A., 2005. A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.380-387.

[19]Fernando, B., Fromont, E., Muselet, D., Sebban, M., 2012. Discriminative Feature Fusion for Image Classification. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.3434-3441.

[20]Geng, X., Zhan, D.C., Zhou, Z.H., 2005. Supervised nonlinear dimensionality reduction for visualization and classification. IEEE Trans. Syst. Man Cybern. B, 35(6):1098-1107.

[21]Guyon, I., Watson, J., Barnhill, S., Vapnik, V., 2002. Gene selection for cancer classification using support vector machines. Mach. Learn., 46(1-3):389-422.

[22]Hancock, T., Mamitsuka, H., 2012. Boosted network classifiers for local feature selection. IEEE Trans. Neur. Networks Learn. Syst., 23(11):1767-1778.

[23]He, R., Tan, T.N., Wang, L., Zheng, W.S., 2012. Regularized Correntropy for Robust Feature Selection. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.2504-2511.

[24]Hyvarinen, A., Oja, E., 2000. Independent component analysis: algorithms and applications. Neur. Networks, 13(4-5):411-430.

[25]Javed, K., Babri, H.A., Saeed, M., 2012. Feature selection based on class-dependent densities for high-dimensional binary data. IEEE Trans. Knowl. Data Eng., 24(3):465-477.

[26]Jurie, F., Triggs, B., 2005. Creating Efficient Codebooks for Visual Recognition. Proc. 10th IEEE Int. Conf. on Computer Vision, p.604-610.

[27]Kadir, T., Zisserman, A., Brady, M., 2004. An affine invariant salient region detector. LNCS, 3021:228-241.

[28]Ke, Y., Sukthankar, R., 2004. PCA-SIFT: a More Distinctive Representation for Local Image Descriptors. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.511-517.

[29]Lazebnik, S., Schmid, C., Ponce, J., 2003. A Sparse Texture Representation Using Affine-Invariant Regions. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.319-324.

[30]Leibe, B., Leonardis, A., Schiele, B., 2008. Robust object detection with interleaved categorization and segmentation. Int. J. Comput. Vis., 77(1-3):259-289.

[31]Li, C.S., Liu, Q.S., Liu, J., Lu, H.Q., 2012. Learning Ordinal Discriminative Features for Age Estimation. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.2570-2577.

[32]Liu, H.W., Sun, J.G., Liu, L., Zhang, H.J., 2009. Feature selection with dynamic mutual information. Pattern Recogn., 42(7):1330-1339.

[33]Lowe, D., 2004. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 60(2):91-110.

[34]Matas, J., Chum, O., Urban, M., Pajdla, T., 2004. Robust wide baseline stereo from maximally stable extremal regions. Image Vis. Comput., 22(10):761-767.

[35]Mikolajczyk, K., Schmid, C., 2001. Indexing Based on Scale Invariant Interest Points. Proc. 8th Int. Conf. on Computer Vision, p.525-531.

[36]Mikolajczyk, K., Schmid, C., 2004. Scale & affine invariant interest point detectors. Int. J. Comput. Vis., 60(1):63-86.

[37]Mikolajczyk, K., Schmid, C., 2005. A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell., 27(10):1615-1630.

[38]Mikolajczyk, K., Leibe, B., Schiele, B., 2005a. Local Features for Object Class Recognition. Proc. 10th IEEE Int. Conf. on Computer Vision, p.1792-1799.

[39]Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., van Gool, L., 2005b. A comparison of affine region detectors. Int. J. Comput. Vis., 65(1-2):43-72.

[40]Mikolajczyk, K., Leibe, B., Schiele, B., 2006. Multiple Object Class Detection with a Generative Model. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, p.26-36.

[41]Mohan, A., Papageorgiou, C., Poggio, T., 2001. Example-based object detection in images by components. IEEE Trans. Pattern Anal. Mach. Intell., 23(4):349-361.

[42]Moosmann, F., Nowak, E., Jurie, F., 2008. Randomized clustering forests for image classification. IEEE Trans. Pattern Anal. Mach. Intell., 30(9):1632-1646.

[43]Nakayama, H., Harada, T., Kuniyoshi, Y., 2010. Global Gaussian Approach for Scene Categorization Using Information Geometry. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.2336-2343.

[44]Neshatian, K., Zhang, M., 2009. Genetic programming for feature subset ranking in binary classification problems. LNCS, 5481:121-132.

[45]Nowak, E., Jurie, F., Triggs, B., 2006. Sampling strategies for bag-of-features image classification. LNCS, 3954:490-503.

[46]Ohba, K., Ikeuchi, K., 1997. Detectability, uniqueness, and reliability of eigen windows for stable verification of partially occluded objects. IEEE Trans. Pattern Anal. Mach. Intell., 19(9):1043-1047.

[47]Pan, H., Li, X.B., Jin, L.Z., Xia, L.Z., 2011. Object description and recognition using multiscale geometric analysis. J. Infrar. Millim. Waves, 30(1):85-90.

[48]Papageorgiou, C., Poggio, T., 2000. A trainable system for object detection. Int. J. Comput. Vis., 38(1):15-33.

[49]Perronnin, F., Dance, C., 2007. Fisher Kernels on Visual Vocabularies for Image Categorization. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.1-8.

[50]Redondo-Cabrera, C., Lopez-Sastre, R.J., Acevedo-Rodriguez, J., Maldonado-Bascon, S., 2012. SURFing the Point Clouds: Selective 3D Spatial Pyramids for Category-Level Object Recognition. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.3458-3465.

[51]Salton, G., Wong, A., Yang, C.S., 1975. A vector space model for automatic indexing. Commun. ACM, 18(11):613-620.

[52]Saul, L.K., Roweis, S.T., 2003. Think globally, fit locally: unsupervised learning of low dimensional manifolds. J. Mach. Learn. Res., 4(2):119-155.

[53]Schaffalitzky, F., Zisserman, A., 2002. Multi-view matching for unordered image sets, or “How do I organize my holiday snaps?”. LNCS, 2350:414-431.

[54]Shlens, J., 2009. A Tutorial on Principal Component Analysis. Center for Neural Science, New York University, New York City, NY. Available from http://www.snl.salk.edu/~shlens/pca.pdf

[55]Tong, S., Koller, D., 2002. Support vector machine active learning with applications to text classification. J. Mach. Learn. Res., 2:45-66.

[56]van Gool, L., Moons, T., Ungureanu, D., 1996. Affine/ photometric invariants for planar intensity patterns. LNCS, 1064:642-651.

[57]Viola, P., Jones, M.J., 2004. Robust real-time face detection. Int. J. Comput. Vis., 57(2):137-154.

[58]Wang, Y.J., Liu, X.B., Jia, Y.D., 2012. Visual word soft-histogram for image representation. J. Softw., 23(7):1787-1795 (in Chinese).

[59]Weber, M., Welling, M., Perona, P., 2000. Unsupervised Learning of Models for Recognition. European Conf. on Computer Vision, p.18-32.

[60]Yang, J., Yang, J.Y., 2003. Why can LDA be performed in PCA transformed space. Pattern Recogn., 36(2):563-566.

[61]Yang, J., Zhang, D., Frangi, A.F., Yang, J.Y., 2004. Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Trans. Pattern Anal. Mach. Intell., 26(1):131-137.

[62]Yang, J., Zhang, D., Yong, X., Yang, J.Y., 2005. Two-dimensional discriminant transform for face recognition. Pattern Recogn., 38(7):1125-1129.

[63]Yu, L., Liu, H., 2004. Efficient feature selection via analysis of relevance and redundancy. J. Mach. Learn. Res., 5:1205-1224.

[64]Zeng, L., Gu, D.L., 2012. A SIFT feature descriptor based on sector area partitioning. Acta Autom. Sin., 38(9):1513-1519 (in Chinese).

[65]Zhang, L.B., Wang, C.H., Xiao, B.H., Shao, Y.X., 2012. Image representation using bag-of-phrases. Acta Autom. Sin., 38(1):46-54 (in Chinese).

[66]Zhang, L.J., Chen, C., Bu, J.J., He, X.F., 2012. A unified feature and instance selection framework using optimum experimental design. IEEE Trans. Image Process., 21(5):2379-2388.

[67]Zhu, Q., Avidan, S., Yeh, M.C., Cheng, K.T., 2006. Fast Human Detection Using a Cascade of Histograms of Oriented Gradients. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.1491-1498.