Journal of Computer, Internet and Network Security ISSN: 2457-0176 (Online)

Authors: Manish Jain, Avnesh Kumar Joshi

Abstract: CBIR system that works on the basis of low level image semantics cannot be directly related to the expressive semantics that is used by human for deciding image similarities. The low-level semantic of the image consists of color, texture and shape of the object inside an image. Now- a- day, one type of feature extraction technique cannot provide the fulfilled result because in the latest trained used the combination of feature techniques. There is generous increase in retrieval precision when combinations of these techniques are used in an effective way. In this paper, propose a comparison on  CBIR system using different feature extraction methods; three features based on color( i.e HSV Histogram, Color Moment) and another two feature computed by applying the texture feature using Gabor Wavelet and Wavelet Transform of the image. For similarity matching between the query image and database images Manhattan distance or City Block or L1 distance is used. The experimental results on WANG database showed higher retrieval efficiency (in terms of precision) when compared with existing methods using color and texture features.