Content Based Image Retrieval Based on Color, Texture and Shape Feature

Abstract

Content Based Image Retrieval (CBIR) is an emergent and evolving trend in image processing. CBIR is
utilized to search and retrieve the query image from extensively variety of database. Many Elements and algorithm can be
utilized for efficient image retrieval. The way toward recovering relevant images is generally gone before by extricating
some segregating highlights that can best describes the database images. In this paper, we propose a CBIR strategy by
separating both color, Texture and shape include vectors utilizing the color histogram, color correlogram ,color moments,
Discrete Wavelet Transform (DWT) and the Gobar wavelet transform. At query time texture vectors are thought about
utilizing a likeness measure which is the Manhattan distance and the most comparable image is retrieved. These low
level elements essentially constitute color, texture and shape features.