Int J Performability Eng ›› 2020, Vol. 16 ›› Issue (9): 1393-1403.doi: 10.23940/ijpe.20.09.p8.13931403

Previous Articles     Next Articles

A Fast and Precise Spatial Verification Strategy for Duplicate Image Retrieval

Ming Chena,*, Zhifeng Zhanga, Tieliang Gaob, Li Duanc, and Junpeng Zhangd   

  1. aSoftware Engineering College, Zhengzhou University of Light Industry, Zhengzhou, 450001, China;
    bSchool of Business, Xinxiang University, Xinxiang, 453000, China;
    cSchool of Computer and Information Technology, Beijing Jiaotong University, Beijing, 100044, China;
    dZhumadian Power Supply Company, State Grid Henan Electric Power Company, Zhumadian, 463000, China
  • Submitted on ; Revised on ; Accepted on
  • Contact: * E-mail address:
  • About author:Ming Chen is a lecturer at Zhengzhou University of Light Industry. His research interests include computer vision and image processing.
    Zhifeng Zhang is an associate professor at Zhengzhou University of Light Industry. His research interests include machine learning.
    Tieliang Gao is an associate professor at Xinxiang University. His research interests include service recommendation.
    Li Duan is a lecturer at Beijing Jiaotong University. Her research interests include service computing, IoT security, and blockchain.
    Junpeng Zhang is a senior engineer at Zhumadian Power Supply Company. His research interests include big data analysis.

Abstract: Spatial verification for duplicate image retrieval is often time-consuming and not sensitive to similar images. To address this problem, we propose a fast and precise spatial verification strategy for duplicate image retrieval. The motivation of this strategy is to use angle and scale information to filter similar images. This is because the matched descriptors of similar images are not transformed according to consistent angles and log-scales. The angle differences and log-scale differences of matched descriptors can be projected to points in two-dimensional space. Intuitively, the two-dimensional point distribution of non-duplicate images is relatively discrete, and the two-dimensional point distribution of duplicate images is relatively concentrated. Therefore, this paper utilizes the inverse cloud algorithm to calculate the discrete degree of the two-dimensional point distribution to exclude the non-duplicate images that have large fluctuation distributions. Then, the new voting algorithm can be used to re-rank the images to improve the retrieval accuracy. The experimental results showed that, compared with traditional algorithms, the new strategy was able to effectively improve retrieval accuracy without adding extra storage overhead and computational overhead.

Key words: spatial verification, duplicate image retrieval, geometric consistency