Image Retrieval Using Weighted Vocabulary Tree with Location Information

doi:10.16182/j.issn1004731x.joss.201710017

Abstract

Abstract: Aiming at the positional information ignorance problem in image retrieval based on SIFT feature matching, an image retrieval approach using weighted vocabulary tree based on the spatial location information was proposed. The vocabulary tree is used in the method to quantify SIFT features as the visual words, converting the image match into the visual words' weight vector match. Because only visual words' weight match ignored the mutual position effect, SIFT points' spatial location information was generated, and was classified into the position effect of visual words according to affiliation between SIFT points and visual words. The spatial location information of the visual words was used as the weighting factor of weight vector matches, refining the matching score between features. Similar images were retrieved by similarity sort. The experimental results show that the algorithm can effectively improve the accuracy of the image retrieval.

Key words: vocabulary tree, location information, vector matching, image retrieval

CLC Number:

TP391

Chen Ying, Guo Jiayu. Image Retrieval Using Weighted Vocabulary Tree with Location Information[J]. Journal of System Simulation, 2017, 29(10): 2353-2360.

References

[1] Kesorn K, Poslad S.An enhanced Bag-of-Visual word vector space model to represent visual content in athletics images[J]. IEEE Trans on Multimedia(S1520-9210), 2012, 14(1): 211-222.
[2] Nistér D, Stewénius H.Scalable recognition with a vocabulary tree[C]// Proc of the IEEE Conference on Computer Vision and Pattern Recognition, New York, USA, June 17-22, 2006. Piscataway, NJ, USA: IEEE, 2006: 2161-2168.
[3] 陈赟, 沈一帆. 基于词汇树的图片搜索[J]. 计算机工程, 2010, 36(6): 189-191.
( Chen Yun, Shen Yifan.Image search based on vocabulary tree[J]. Computer Engineering, 2010, 36(6): 189-191.)
[4] Jégou H, Douze M, Schmid C.Improving bag-of-feature for large scale image search[J]. Int'l Journal of Computer Vision(S1573-1405), 2010, 87(3): 316-336.
[5] Qin Jianzhao, Yung N H C. Scene categorization via contextual visual words[J]. Pattern Recognition ISSN号(S0031-3203), 2010, 43(5): 1874-1888.
[6] Tang Wenbin, Cai Rui, Li Zhiwei, et al.Contextual synonym dictionary for visual object retrieval[C]// Proc of the 19th International Conference on Multi Media. Scottsdale, USA, Nov 28- Dec 1, 2011. Scottsdale, USA: ACM Multimedia, 2011: 503-512.
[7] Wang Xiaoyu, Yang Ming, Cour T, et al.Contextual weighting for vocabulary tree based image retrieval[C]// Proc of the 13th IEEE International Conference on Computer Vision, Barcelona, Spain, Nov 6-13, 2011. Piscataway, NJ, USA: IEEE, 2011: 209-216.
[8] 朱道广, 郭志刚, 赵勇威. 基于空间上下文加权词汇树的图像检索方法[J]. 模式识别与人工智能, 2013, 26(11): 1050-1056.
(Zhu Daoguang, Guo Zhigang, Zhao Yongwei.Image Retrieval with Spatial Context Weighting Based Vocabulary Tree[J]. Pattern Recognition and Artificial Intelligence, 2013, 26(11): 1050-1056 .)
[9] Jégou H, Douze M, Schmid C.Hamming embedding and weak geometric consistency for large scale image search[C]// The 10th European Conference on Computer Vision, Marseille, France, 2008. Heidelberg, Berlin, Germany: Springer, 2008: 304-317.
[10] Deng J, Dong W, Socher R, et al.ImageNet: A large-scale hierarchical image database[C]// IEEE International Conference on Computer Vision and Pattern Recognition, CVPR 2008. Anchorage, Alaska, USA, June 20-26, 2009. Piscataway, NJ, USA: IEEE, 2009: 248-255