An efficient CBIR system based on color histogram, edge, and texture features

Abstract

SummaryContent‐based image retrieval (CBIR) has been popular in recent times due to the necessity of storing large database of images in information processing and biomedical applications. However, the accurate retrieval of images and retrieval time are the two major challenges in CBIR systems. Most of the existing works focus on searching the whole database; hence, the retrieval process becomes a time consuming process. This paper proposes an efficient CBIR system, which retrieves images accurately with reasonable retrieval time using the combination of color histogram, edge, and texture features. Initially, the searching is done based on the color similarity and texture using modified Color Difference Histogram (CDH). Then, an edge orientation technique is applied only on the identified images to create a combined feature space. This process greatly reduces the time required for retrieval process due to the absence of fusion process which is quite normal in CBIR systems. Simulations are conducted on the standard databases to show the superior performance of the proposed CBIR system in terms of retrieval time and accuracy.