Enhancing the retrieval performance by combing the texture and edge features

TL;DR

This paper introduces a new image retrieval algorithm combining geometrical moments and local binary patterns, resulting in improved accuracy over existing methods.

Contribution

The paper proposes a novel CBIR algorithm that integrates geometrical moments with LBP to enhance retrieval performance.

Findings

Significant improvement over LBP alone

Better evaluation measures compared to existing techniques

Effective combination of texture and edge features

Abstract

In this paper, anew algorithm which is based on geometrical moments and local binary patterns (LBP) for content based image retrieval (CBIR) is proposed. In geometrical moments, each vector is compared with the all other vectors for edge map generation. The same concept is utilized at LBP calculation which is generating nine LBP patterns from a given 3x3 pattern. Finally, nine LBP histograms are calculated which are used as a feature vector for image retrieval. Moments are important features used in recognition of different types of images. Two experiments have been carried out for proving the worth of our algorithm. The results after being investigated shows a significant improvement in terms of their evaluation measures as compared to LBP and other existing transform domain techniques.