Title: Line edge binary patterns for content-based image retrieval

Authors: P.V.N. Reddy; K. Satya Prasad

Addresses: Department of Electronics and Communication Engineering, Jawaharlal Nehru Technological University, Kakinada, Andhra Pradesh, India ' Department of Electronics and Communication Engineering, Jawaharlal Nehru Technological University, Kakinada, Andhra Pradesh, India

Abstract: In this paper, a new algorithm known as Line Edge Binary Pattern (LEBP) is proposed for Content-Based Image Retrieval (CBIR). The proposed method represents the local region of an image based on the distribution of line edges in contrast to Local Binary Patterns (LBPs). LBPs extract information based on the distribution of point edges which are evaluated by taking into consideration local differences between the centre pixel and its neighbours in an image. The retrieval results of the proposed method are tested on Corel 1000 and Corel 2450 image databases in terms of precision and recall. The results after being investigated show a significant improvement in terms of precision and recall as compared to LBP and other existing spatial and transform domain methods.

Keywords: line edge binary patterns; local binary patterns; CBIR; content-based image retrieval.

DOI: 10.1504/IJSISE.2012.049857

International Journal of Signal and Imaging Systems Engineering, 2012 Vol.5 No.3, pp.227 - 235

Available online: 17 Oct 2012 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article