Abstract The bundle feature based method is effective for near-duplicate image retrieval. However, there are some limitations due to the use of SIFT descriptor and coordinate information. Therefore, in this paper color features are integrated into traditional SIFT representation to form the multi-features bundle and two kinds of robust orders between points in bundle feature are introduced-the circle order and the main orientation order. Firstly, the color distribution features of interesting points are extracted and indexing is embedded into them, and then the potential false matchings are discarded by the Kullback-Leibler divergence of corresponding color features. Secondly, the geometric loss score is computed according to the inconsistency between orders of the distance from points to the center of bundle region or the orders of the angle between the orientation of points and main orientation of bundle. The experiment on Copydays dataset shows the improved retrieval performance by adding color features and better circle order and main orientation order geometric constraints of the bundle feature in the image retrieval task.
Fund:Supported by National Natural Science Foundation of China (No.61373060)
About author:: (SONG Ge, born in 1991, master student. His research inte-rests include image retrieval and computer vision.) (JIN Xin, born in 1987, Ph.D. candidate. His research inte-rests include pattern recognition and computer vision.) (TAN Xiaoyang(Corresponding author), born in 1971, Ph.D., professor. His research interests include face recognition, machine learning, pattern recognition and computer vision.)
[1] SIVIC J, ZISSERMAN A. Video Google: A Text Retrieval Approach to Object Matching in Videos // Proc of the 9th IEEE International Conference on Computer Vision. New York, USA: IEEE, 2003: 1470-1477. [2] LOWE D G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110. [3] NISTR D, STEWNIUS H. Scalable Recognition with a Vocabulary Tree // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2006, II: 2161-2168. [4] JGOU H, DOUZE M, SCHMID C. On the Burstiness of Visual Elements // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2009: 1169-1176. [5] ZHANG S L, TIAN Q, HUA G, et al. Descriptive Visual Words and Visual Phrases for Image Applications // Proc of the 17th ACM International Conference on Multimedia. New York, USA: ACM, 2009: 75-84. [6] PHILBIN J, CHUM O, ISARD M, et al. Object Retrieval with Large Vocabularies and Fast Spatial Matching // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2007: 1-8. [7] ZHENG L, WANG S J. Visual Phraselet: Refining Spatial Constraints for Large Scale Image Search. IEEE Signal Processing Le-tters, 2013, 20(4): 391-394. [8] ZHOU W G, LU Y J, LI H Q, et al. Spatial Coding for Large Scale Partial-Duplicate Web Image Search // Proc of the 18th ACM International Conference on Multimedia. New York, USA: ACM, 2010: 511-520. [9] YAO J L, YANG B, ZHU Q M. Near-Duplicate Image Retrieval Based on Contextual Descriptor. IEEE Signal Processing Letters, 2015, 22(9): 1404-1408. [10] CAO Y, WANG C H, LI Z W, et al. Spatial-Bag-of-Features // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2010: 3352-3359. [11] KHAN F S, ANWER R M, VAN DE WEIJER J, et al. Color Attributes for Object Detection // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2012: 3306-3313. [12] ZHENG Y, ZHANG Y J, LAROCHELLE H. Topic Modeling of Multimodal Data: An Autoregressive Approach // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Re-cognition. New York, USA: IEEE, 2014: 1370-1377. [13] NIU Z X, HUA G, GAO X B, et al. Context aware Topic Model for Scene Recognition // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2012: 2743-2750. [14] WENGERT C, DOUZE M, JGOU H. Bag-of-Colors for Improved Image Search // Proc of the 19th ACM International Conference on Multimedia. New, USA: ACM, 2011: 1437-1440. [15] ZHENG L, WANG S J, LIU Z Q, et al. Packing and Padding: Coupled Multi-index for Accurate Image Retrieval // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2014: 1947-1954. [16] WU Z, KE Q E, ISARD M, et al. Bundling Features for Large Scale Partial-Duplicate Web Image Search // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Re-cognition. New York, USA: IEEE, 2009: 25-32. [17] MATAS J, CHUM O, URBAN M, et al. Robust Wide-Baseline Stereo from Maximally Stable Extremal Regions. Image and Vision Computing, 2004, 22(10): 761-767. [18] VAN DE WEIJER J, SCHMID C, VERBEEK J, et al. Learning Color Names for Real-World Applications. IEEE Trans on Image Processing, 2009, 18(7): 1512-1523. [19] MANNING C D, RAGHAVAN P, SCH TZE H, et al. Introduction to Information Retrieval. Cambridge, UK: Cambridge University Press, 2008. [20] JEGOU H, DOUZE M, SCHMID C. Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search // Proc of the 10th European Conference on Computer Vision. Berlin, Germany: Springer, 2008, I: 304-317. [21] HUISKES M J, THOMEE B, LEW M S. New Trends and Ideas in Visual Concept Detection: The MIR Flickr Retrieval Evaluation Initiative // Proc of the International Conference on Multimedia Information Retrieval. New York, USA: ACM, 2010: 527-536.
2016, Vol. 29 
