Color based compact hierarchical image representation
ZHU Jie1, WU Shufang2,3, XIE Bojun4, MA Liyan5
1. Department of Information Management, the National Police University for Criminal Justice, Baoding Hebei 071000, China; 2. College of Management and Economics, Tianjin University, Tianjin 300072, China; 3. College of Management, Hebei University, Baoding Hebei 071000, China; 4. College of Mathematics and Information Science, Hebei University, Baoding Hebei 071000, China; 5. Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, China
Abstract：The spatial pyramid matching method provides the spatial information by splitting an image into different cells. However, spatial pyramid matching can not match different parts of the objects well. A hierarchical image representation method based on Color Level (CL) was proposed. The class-specific discriminative colors of different levels were obtained from the viewpoint of feature fusion in CL algorithm, and then an image was iteratively split into different levels based on these discriminative colors. Finally, image representation was constructed by concatenating the histograms of different levels. To reduce the dimensionality of image representation, the Divisive Information-Theoretic feature Clustering (DITC) method was used to cluster the dictionary, and the generated compact dictionary was used for final image representation. Classification results on Soccer, Flower 17 and Flower 102 datasets, demonstrate that the proposed method can obtain satisfactory results in these datasets.
[1] CSURKA G, DANCE C R, FAN L X, et al. Visual categorization with bags of keypoints[C]//Proceedings of the 8th European Conference on Computer Vision. Piscataway, NJ:IEEE, 2004:1-22. [2] OKAWA M. Offline signature verification based on bag-of-visual words model using KAZE features and weighting schemes[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway, NJ:IEEE, 2016:184-190. [3] 杨浩,张永.基于优化视觉词袋模型的图像分类方法[J].计算机应用, 2017, 37(8):2244-2247.(YANG H, ZHANG Y. A image classification method by optimizing bag-of-visual words model[J]. Journal of Computer Applications, 2017, 37(8):2244-2247.) [4] BERG A C, BERG T L, MALIK J. Shape matching and object recognition using low distortion correspondences[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2005:26-33. [5] 生海迪,段会川,孔超.基于语义短语的空间金字塔词袋模型图像分类方法[J].小型微型计算机系统,2015,36(4):877-881.(SHENG H D, DUAN H C, KONG C. Spatial pyramid bag-of-words model for image classification based on semantic phrases[J]. Journal of Chinese Computer Systems, 2015, 36(4):877-881.) [6] 陈莹,高含.采用空间词袋模型的图像分类方法[J].小型微型计算机系统,2016,37(9):2099-2103.(CHEN Y, GAO H. Image classification method based on spatial bag of words model[J].Journal of Chinese Computer Systems, 2016, 37(9):2099-2103.) [7] LI T, MEI T, KWEON I S, et al. Contextual bag-of-words for visual categorization[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2011, 21(4):381-392. [8] FENG J, NI B, XU D, et al. Histogram contextualization[J]. IEEE Transactions on Image Processing, 2012, 21(2):778-788. [9] TANG P, ZHANG J, WANG X, et al. Learning extremely shared middle-level image representation for scene classification[J]. Knowledge and Information Systems, 2017, 52(2):509-530. [10] TANG P, WANG X, FENG B, et al. Learning multi-instance deep discriminative patterns for image classification[J]. IEEE Transactions on Image Processing, 2016, 26(7):3385-3396. [11] LAZEBNIK S, SCHMID C, PONCE J. Beyond bags of features:Spatial pyramid matching for recognizing natural scene categories[C]//Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2006:2169-2178. [12] DHILLON I S, MALLELA S, KUMAR R, et al. A divisive information-theoretic feature clustering algorithm for text classification[J]. Journal of Machine Learning Research, 2003, 3(3):1265-1287. [13] KHAN F S, RAO M A, WEIJER J V D, et al. Coloring action recognition in still images[J]. International Journal of Computer Vision, 2013, 105(3):205-221. [14] GAVVES E, FERNANDO B, SNOEK C G M, et al. Fine-grained categorization by alignments[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2013:1713-1720. [15] ZHOU Y, WEI Y. Learning hierarchical spectral-spatial features for hyperspectral image classification[J]. IEEE Transactions on Cybernetics, 2016, 46(7):1667. [16] ELFIKY N M, KHAN F S, VAN DE WEIJER J, et al. Discriminative compact pyramids for object and scene recognition[J]. Pattern Recognition, 2012, 45(4):1627-1636. [17] VAN DE WEIJER J, SCHMID C, VERBEEK J, et al. Learning color names for real-world applications[J]. IEEE Transactions on Image Processing, 2009, 18(7):1512-1523. [18] VAN DE WEIJER J, SCHMID C. Coloring local feature extraction[C]//Proceedings of Computer Vision-ECCV 2006. Berlin:Springer, 2006:334-348. [19] LOWE D G. Distinctive image features from scale-invariant points[J]. International Journal of Computer Vision, 2004, 60(2):91-110. [20] FERNANDO B, FROMONT E, MUSELET D, et al. Discriminative feature fusion for image classification[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2012:3434-3441. [21] NILSBACK M E, ZISSERMAN A. A visual vocabulary for flower classification[C]//Proceedings of the 19th IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2006:1447-1454. [22] GEHLER P, NOWOZIN S. On feature combination for multiclass object classification[C]//Proceedings of the 2009 IEEE 12th International Conference on Computer Vision. Piscataway, NJ:IEEE, 2009:221-228. [23] VORAVUTHIKUNCHAI W, CRÉMILLEUX B, JURIE F. Histograms of pattern sets for image classification and object recognition[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2014:224-231. [24] FERNANDO B, FROMONT E, TUYTELAARS T. Mining mid-level features for image classification[J]. International Journal of Computer Vision, 2014, 108(3):186-203. [25] YUAN X T, LIU X, YAN S. Visual classification with multitask joint sparse representation[J]. IEEE Transactions on Image Processing, 2012, 21(10):4349-4360. [26] YE G, LIU D, JHUO I H, et al. Robust late fusion with rank minimization[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2012:3021-3028. [27] NILSBACK M E, ZISSERMAN A. Automated flower classification over a large number of classes[C]//Proceedings of the 6th Indian Conference on Computer Vision, Graphics & Image Processing. Piscataway, NJ:IEEE, 2008:722-729. [28] WANG Z, FENG J, YAN S. Collaborative linear coding for robust image classification[J]. International Journal of Computer Vision, 2015, 114(2/3):322-333. [29] ANGELOVA A, ZHU S. Efficient object detection and segmentation for fine-grained recognition[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2013:811-818. [30] FU Z, ROBLES-KELLY A, ZHOU J. MILIS:multiple instance learning with instance selection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5):958-977. [31] ZHANG L, ZHANG D. Visual understanding via multi-feature shared learning with global consistency[J]. IEEE Transactions on Multimedia, 2016, 18(2):247-259. [32] MINH H Q, BAZZANI L, MURINO V. A unifying framework in vector-valued reproducing kernel Hilbert spaces for manifold regularization and co-regularized multi-view learning[J]. Journal of Machine Learning Research, 2016, 17(1):769-840. [33] XIE G S, ZHANG X Y, SHU X, et al. Task-driven feature pooling for image classification[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2015:1179-1187. [34] XIE L, WANG J, ZHANG B, et al. Incorporating visual adjectives for image classification[J]. Neurocomputing, 2016, 182(C):48-55.
2017, Vol. 37 
