Image Retrieval Based on Binary Signature ang S-kGraph

TL;DR

This paper presents a binary signature encoding and S-kGraph classification method to improve the efficiency of region-based image retrieval in large databases, demonstrated on COREL images.

Contribution

It introduces a binary signature encoding combined with S-kGraph classification to reduce computational costs in region-based image retrieval.

Findings

Improved retrieval accuracy using region-based approach

Reduced computational cost with binary signatures

Effective classification with S-kGraph

Abstract

In this paper, we introduce an optimum approach for querying similar images on large digital-image databases. Our work is based on RBIR (region-based image retrieval) method which uses multiple regions as the key to retrieval images. This method significantly improves the accuracy of queries. However, this also increases the cost of computing. To reduce this expensive computational cost, we implement binary signature encoder which maps an image to its identification in binary. In order to fasten the lookup, binary signatures of images are classified by the help of S-kGraph. Finally, our work is evaluated on COREL's images.