Efficient and Effective Similar Shape Retrieval

  • Authors:

  • Jia Wang;Wendy Chang;Raj Acharya

  • Affiliations:

  • LG Electronics Research Center of America;Rochester Institute of Technology;State University of New York at Buffalo

  • Venue:
  • ICMCS '99 Proceedings of the IEEE International Conference on Multimedia Computing and Systems - Volume 2
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we present the design and implementation of a content-based retrieval system which achieves efficient and effective similar shape retrieval using a modified geometric hashing technique. The system contains four main components: a feature acquisition module, a query manager, a search engine, and a hash table. The hash table houses the feature information. The query manager accepts the user query and extracts contours from the query image. The feature acquisition module transforms and quantizes the image contours and formulates the hash table entries. Given a visual query, the search agent derives a list of potentially similar shape images by searching the hash table using a majority voting algorithm. Extensive experiments have been conducted to demonstrate that the proposed designs offer a viable and practical approach to similar shape retrieval.