Image Retrieval Using Weighted Vocabulary Tree with Location Information

Authors

Chen Ying, Key Laboratory of Advanced Control Light Process, Jiangnan University, Wuxi 214000, China;
Jiayu Guo, Key Laboratory of Advanced Control Light Process, Jiangnan University, Wuxi 214000, China;

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.

Recommended Citation

Ying, Chen and Guo, Jiayu (2020) "Image Retrieval Using Weighted Vocabulary Tree with Location Information," Journal of System Simulation: Vol. 29: Iss. 10, Article 17.
DOI: 10.16182/j.issn1004731x.joss.201710017
Available at: https://dc-china-simulation.researchcommons.org/journal/vol29/iss10/17

First Page

2353

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.201710017

Last Page

2360

CLC

TP391

Recommended Citation

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

DOI

10.16182/j.issn1004731x.joss.201710017