RBIR using Interest Regions and Binary Signatures

TL;DR

This paper presents a novel RBIR method that uses interest regions detected by Harris-Laplace and encodes images into binary signatures for improved accuracy and efficiency in image retrieval.

Contribution

It introduces a new RBIR approach combining interest region detection with binary signature encoding and an S-tree retrieval algorithm, enhancing CBIR accuracy.

Findings

Improved retrieval accuracy over global feature methods

Efficient image storage and retrieval using binary signatures

Effective evaluation on COREL image dataset

Abstract

In this paper, we introduce an approach to overcome the low accuracy of the Content-Based Image Retrieval (CBIR) (when using the global features). To increase the accuracy, we use Harris-Laplace detector to identify the interest regions of image. Then, we build the Region-Based Image Retrieval (RBIR). For the efficient image storage and retrieval, we encode images into binary signatures. The binary signature of a image is created from its interest regions. Furthermore, this paper also provides an algorithm for image retrieval on S-tree by comparing the images' signatures on a metric similarly to EMD (earth mover's distance). Finally, we evaluate the created models on COREL's images.