RBIR Based on Signature Graph

TL;DR

This paper introduces a region-based image retrieval system utilizing signature graphs and Harris-Laplace interest points, employing binary signatures and Earth Mover's Distance for efficient image classification and retrieval.

Contribution

It presents a novel RBIR method using signature graphs and binary signatures, improving retrieval speed and storage efficiency over large image databases.

Findings

Effective retrieval on Corel database with over 10,000 images

Reduced storage space and query time through binary signatures

High accuracy in image classification using signature graphs

Abstract

This paper approaches the image retrieval system on the base of visual features local region RBIR (region-based image retrieval). First of all, the paper presents a method for extracting the interest points based on Harris-Laplace to create the feature region of the image. Next, in order to reduce the storage space and speed up query image, the paper builds the binary signature structure to describe the visual content of image. Based on the image's binary signature, the paper builds the SG (signature graph) to classify and store image's binary signatures. Since then, the paper builds the image retrieval algorithm on SG through the similar measure EMD (earth mover's distance) between the image's binary signatures. Last but not least, the paper gives an image retrieval model RBIR, experiments and assesses the image retrieval method on Corel image database over 10,000 images.