CSIFT based locality-constrained linear coding for image classification

详细信息    查看全文

• 作者：Junzhou Chen (1)
  Qing Li (1)
  Qiang Peng (1)
  Kin Hong Wong (2)
  
  1. School of Information Science and Technology ; Southwest Jiaotong University ; Chengdu ; 610031 ; Sichuan ; China
  2. Department of Computer Science and Engineering ; The Chinese University of Hong Kong ; Shatin ; Hong Kong
  
• 关键词：CSIFT ; Sparse coding ; LLC ; Image classification
• 刊名：Pattern Analysis & Applications
• 出版年：2015
• 出版时间：May 2015
• 年：2015
• 卷：18
• 期：2
• 页码：441-450
• 全文大小：758 KB
• 参考文献：1. Lowe, DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60: pp. 91-110 CrossRef
  2. Geusebroek J-M, van den Boomgaard R, Smeulders AWM, Geerts H (2001) Color invariance. IEEE Trans Pattern Anal Mach Intell 23(12):1338鈥?350
  3. Abdel-Hakim AE, Farag AA (2006) Csift: a sift descriptor with color invariant characteristics. In: 2006 IEEE computer society conference on computer vision and pattern recognition, vol 2. IEEE, pp 1978鈥?983
  4. Van De Weijer J, Gevers T, Bagdanov AD (2006) Boosting color saliency in image feature detection. IEEE Trans Pattern Anal Mach Intell 28(1):150鈥?56
  5. Burghouts, GJ, Geusebroek, J-M (2009) Performance evaluation of local colour invariants. Comput Vis Image Underst 113: pp. 48-62 CrossRef
  6. Gevers T, Gijsenij A, Van de Weijer J, Geusebroek J-M (2012) Color in computer vision: fundamentals and applications, vol 24. Wiley, New York
  7. Goldfarb, D, Idnani, A (1983) A numerically stable dual method for solving strictly convex quadratic programs. Math Program 27: pp. 1-33 CrossRef
  8. Csurka G, Dance C, Fan L, Willamowski J, Bray C (2004) Visual categorization with bags of keypoints. In: Workshop on statistical learning in computer vision, ECCV, vol 1, pp 22
  9. Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: 2006 IEEE computer society conference on computer vision and pattern recognition, vol 2. IEEE, pp 2169鈥?178
  10. Shabou A, LeBorgne H (2012) Locality-constrained and spatially regularized coding for scene categorization. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 3618鈥?625
  11. Yang J, Yu K, Gong Y, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009. IEEE, pp 1794鈥?801
  12. Yu, K, Zhang, T, Gong, Y (2009) Nonlinear learning using local coordinate coding. Adv Neural Inf Process Syst 22: pp. 2223-2231
  13. Wang J, Yang J, Yu K, Lv F, Huang T, Gong Y (2010) Locality-constrained linear coding for image classification. In: 2010 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 3360鈥?367
  14. Yang J, Yu K, Huang T (2010) Supervised translation-invariant sparse coding. In: 2010 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 3517鈥?524
  15. Liu L, Wang L, Liu X (2011) In defense of soft-assignment coding. In: 2011 IEEE international conference on computer vision (ICCV). IEEE, pp 2486鈥?493
  16. Yang M, Zhang L, Feng X, Zhang D (2011) Fisher discrimination dictionary learning for sparse representation. In: 2011 IEEE international conference on computer vision (ICCV). IEEE, pp 543鈥?50
  17. Shafer, SA (1985) Using color to separate reflection components. Color Res Appl 10: pp. 210-218 CrossRef
  18. Gevers T, Van De Weijer J, Stokman H et al (2007) Color feature detection. Color image processing: methods and applications, pp 203鈥?26
  19. Gevers T, Smeulders WM et al (1999) Color based object recognition. Pattern Recognit 32(3):453鈥?64
  20. van de Sande KEA, Gevers T, Snoek CGM (2010) Evaluating color descriptors for object and scene recognition. IEEE Trans Pattern Anal Mach Intell 32(9):1582鈥?596
  21. Lowe DG (1999) Object recognition from local scale-invariant features. In: The proceedings of the seventh IEEE international conference on computer vision, vol 2. IEEE, pp 1150鈥?157
  22. Bosch, A, Zisserman, A, Muoz, X (2008) Scene classification using a hybrid generative/discriminative approach. IEEE Trans Pattern Anal Mach Intell 30: pp. 712-727 CrossRef
  23. Hering, E (1964) Outlines of a theory of the light sense. Harvard University Press, Cambridge
  24. Fei-Fei, L, Fergus, R, Perona, P (2006) One-shot learning of object categories. IEEE Trans Pattern Anal Mach Intell 28: pp. 594-611 CrossRef
  25. Griffin G, Holub A, Perona P (2007) Caltech-256 object category dataset
  26. Fan, R-E, Chang, K-W, Hsieh, C-J, Wang, X-R, Lin, C-J (2008) Liblinear: a library for large linear classification. J Mach Learn Res 9: pp. 1871-1874
  27. Khan R, Van de Weijer J, Khan FS, Muselet D, Ducottet C, Barat C (2013) Discriminative color descriptors. In: 2013 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2866鈥?873
  
• 刊物类别：Computer Science
• 刊物主题：Pattern Recognition
  
• 出版者：Springer London
• ISSN：1433-755X

文摘

In the past decade, SIFT descriptor has been witnessed as one of the most robust local invariant feature descriptors and widely used in various vision tasks. Most traditional image-classification systems depend on the gray-based SIFT descriptors, which only analyze the gray level variations of the images. Misclassification may happen since their color contents are ignored. In this article, we concentrate on improving the performance of existing image-classification algorithms by adding color information. To achieve this purpose, different kinds of colored SIFT descriptors are introduced and implemented. locality-constrained linear coding (LLC), a state-of-the-art sparse coding technology, is employed to construct the image-classification system for the evaluation. Moreover, we propose a simple \(\ell _2\) -norm regularized local distance to improve the traditional LLC method. The real experiments are carried out on several benchmarks. With the enhancements to color SIFT and \(\ell _2\) -norm regularization, the proposed image-classification system obtains approximately \(2\,\%\) improvement of classification accuracy on the Caltech-101 dataset and approximately \(5\,\%\) improvement of classification accuracy on the Caltech-256 dataset.