Image Classification Method by Combining Multi-features and Sparse Coding
LUO Hui-Lan1, GUO Min-Jie1, KONG Fan-Sheng2
1.Faculty of Information Engineering, Jiangxi University of Science and Technology, Ganzhou 341000 2.College of Computer Science and Technology, Zhejiang University, Hangzhou 310027
Abstract Using a single image feature to describe the image content is one-sided because of the insufficient information. Besides, the single coding method usually loses the spatial information. To solve these problems, an approach of integrating multi-features and sparse coding methods is proposed. Images are firstly divided into sub regions according to the spatial pyramid, and then the complementary advantages of scale invariant feature transform and the histogram of oriented gradients features are combined to produce various feature sets. Then, different clustering methods are used on different feature sets to acquire different codebooks. Next, two sparse coding methods, locality constrained linear coding and sparse coding based on each codebook are further employed respectively to get various image description sets. Finally, linear support vector machines are applied to image classification, and a voting method is used to determine the final classification. Experimental results show that the proposed method has good accuracy and robustness compared with some state-of-the-art methods.
[1] Qi X J, Han Y T. Incorporating Multiple SVMs for Automatic Image Annotation. Pattern Recognition, 2007, 40(2): 728-741 [2] Gabriella C, Dance C R, Fan L X, et al. Visual Categorization with Bags of Keypoints // Proc of the Workshop on Statistical Learning in Computer Vision. Prague, Czech Republic, 2004: 1-22 [3] Lazebnik S, Schmid C, Ponce J. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA, 2006, II: 2169-2178 [4] Hao K. Image Feature Extraction and Its Application via Sparse Coding. Master Dissertation. Hangzhou, China: Zhejiang University, 2012 (in Chinese) (郝 凯.基于稀疏编码的图像视觉特征提取及应用.硕士学位论文.杭州:浙江大学, 2012) [5] Harzallah H, Jurie F, Schmid C. Combining Efficient Object Loca-lization and Image Classification // Proc of the 12th IEEE International Conference on Computer Vision. Kyoto, Japan, 2009: 237-244 [6] Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110 [7] Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005, I: 886-893 [8] Jiang Y, Wang R S. Scene Classification Based on Multi-feature Extended pLSA Model. Signal Processing, 2010, 26(4): 539-544 (in Chinese) (江 悦,王润生.基于多特征扩展pLSA模型的场景图像分类.信号处理, 2010, 26(4): 539-544) [9] Gao C X, Sang N. Unifying Local Features and Filterbank Features in the Spatial Pyramid Matching Model. Acta Electronica Sinica, 2011, 39(9): 2034-2038 (in Chinese) (高常鑫,桑 农.整合局部特征和滤波器特征的空间金字塔匹配模型.电子学报, 2011, 39(9): 2034-2038) [10] Fu Y, Xian Y M. Image Classification Based on Multi-feature and Improved SVM Ensemble. Computer Engineering, 2011, 37(21): 196-199 (in Chinese) (付 燕,鲜艳明.基于多特征和改进SVM集成的图像分类.计算机工程, 2011, 37(21): 196-199) [11] Lee H, Battle A, Raina R, et al. Efficient Sparse Coding Algorithms[EB/OL]. [2012-12-12]. http://machinelearning.wustl.edu/mlpapers/paper_files/NIPS2006_878.pdf [12] Wang J J, Yang J C, Yu K, et al. Locality-Constrained Linear Coding for Image Classification // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, USA, 2010: 3360-3367 [13] Yang J C, Yu K, Gong Y H, et al. Linear Spatial Pyramid Ma-tching Using Sparse Coding for Image Classification // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 1794-1801 [14] Cui Z. Cooperative Intrusion Detection System Based on Sparse Coding and Multi-class Support Vector Machine. Computer Engineering and Design, 2011, 32(11): 3606-3612 (in Chinese) (崔 振.基于稀疏编码和多类SVM的入侵检测.计算机工程与设计, 2011, 32(11): 3606-3612) [15] Yang M, Wang F. A Classifier Ensemble Algorithm Based on Local Random Subspace. Pattern Recognition and Artificial Intelligence, 2012, 25(4): 595-603 (in Chinese) (杨 明,王 飞.一种基于局部随机子空间的分类集成算法.模式识别与人工智能, 2012, 25(4): 595-603) [16] Tao Y, Zeng Z Y, Yu J K, et al. Completeness Proof and Implementation of Parallel k-means Clustering Algorithm. Computer Engineering, 2010, 36(22): 72-74 (in Chinese) (陶 冶,曾志勇,余建坤,等.并行k均值聚类算法的完备性证明与实现.计算机工程, 2010, 36(22): 72-74) [17] Moosmann F, Triggs B, Jurie F. Fast Discriminative Visual Codebooks Using Randomized Clustering Forests[EB/OL]. [2012-12-12]. http://eprints.pascal-network.org/archive/00002438/01/nips.pdf [18] Luo H L. Clustering Integration Theory and Its Application in Image Classification. Beijing, China: Science Press, 2012 (in Chinese) (罗会兰.聚类集成理论与其在图像分类中的应用.北京:科学出版社, 2012) [19] Yu K, Zhang T, Gong Y H. Nonlinear Learning Using Local Coordinate Coding[EB/OL]. [2012-12-12]. http://www.dbs.informatik.uni-muenchen.de/~yu_k/nips09_lcc.pdf [20] Li F F, Fergus R, Perona P. Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories. Computer Vision and Image Understanding, 2007, 106(1): 59-70 [21] Griffin G, Holub A, Perona P. Caltech-256 Object Category Dataset[DB/OL]. [2012-12-12]. http://authors.library.caltech.edu/7694/1/CNS-TR-2007-001.pdf [22] Li F F, Perona P. A Bayesian Hierarchical Model for Learning Natural Scene Categories // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005, II: 524-531 [23] Oliva A, Aotonio T. Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope. International Journal of Computer Vision, 2001, 42(3): 145-175 [24] Chang C C, Lin C J. LIBSVM: A Library for Support Vector Machines. ACM Trans on Intelligent Systems and Technology, 2011, 2(3): 1-25 [25] Gemert J C, Geusebroek J M, Veenman C J, et al. Kernel Codebooks for Scene Categorization // Proc of the 10th European Confe-rence on Computer Vision. Marseille, France, 2008, III: 696-709 [26] Qi X Z, Wang Q. An Image Classification Approach Based on Sparse Coding and Multiple Kernel Learning. Acta Electronica Si-nica, 2012, 40(4): 773-779 (in Chinese) (亓晓振,王 庆.一种基于稀疏编码的多核学习图像分类方法.电子学报, 2012, 40(4): 773-779)
2014, Vol. 27 
