Color Directional Local Quinary Patterns for Content Based Indexing and Retrieval

Santosh Kumar Vipparthi,Shyam Krishna Nagar

doi:10.1186/s13673-014-0006-x

Abstract

AbstractThis paper presents a novel evaluationary approach to extract color-texture features for image retrieval application namely Color Directional Local Quinary Pattern (CDLQP). The proposed descriptor extracts the individual R, G and B channel wise directional edge information between reference pixel and its surrounding neighborhoods by computing its grey-level difference based on quinary value (−2, −1, 0, 1, 2) instead of binary and ternary value in 0°, 45°, 90°, and 135° directions of an image which are not present in literature (LBP, LTP, CS-LBP, LTrPs, DExPs, etc.). To evaluate the retrieval performance of the proposed descriptor, two experiments have been conducted on Core-5000 and MIT-Color databases respectively. The retrieval performances of the proposed descriptor show a significant improvement as compared with standard local binary pattern LBP, center-symmetric local binary pattern (CS-LBP), Directional binary pattern (DBC) and other existing transform domain techniques in IR system.

Highlights

With the radical expansion of the digitization in the living world, it has become imperative to find a method to browse and search images efficiently from immense database
The retrieval performances show a significant improvement nearly 10.78% in terms of average retrieval precision (ARP) on Corel-5000 database and 9.12% improvement on MIT-Color database in terms of average retrieval rate (ARR) as compared with local binary pattern (LBP)
Experimental results and discussions In image retrieval, various datasets are used for several purposes; these includes Corel dataset, MIT dataset and Brodtz texture dataset etc

Summary

Introduction

With the radical expansion of the digitization in the living world, it has become imperative to find a method to browse and search images efficiently from immense database. Section “Experimental results and discussions”, presents the retrieval performances of proposed descriptor and other state-of-the art techniques on two bench mark datasets (Corel-5000 and MIT-Color). Local patterns with proposed Descriptor The concept of LBP [17], LTP [21] and DBC [29] has been utilized to extract texture features (DLQP) from individual color channels (R, G and B) to generate a new colortexture feature called CDLQP.

Results

Conclusion