Content Based Image Retrieval Method using Color, Texture and Shape Features based on Re-weighting Factor

Abstract

In recent years, the quantity of the digital image collection is growing rapidly due to the development of the internet and the availability of image capturing devices. The problem arises when retrieving these images from storage media. Thus, image retrieval system become efficient tools for managing large image databases. A content based image retrieval system allows the user to present a query image in order to retrieve images stored in the database according to their similarity to the query image. In this study, we have proposed a content based image retrieval method that uses a combination of color histogram, color moment, Gabor filter, and Canny's edge. The color histogram, and color moment are used for color features, Gabor filter is used for texture feature extraction, and for shape feature extraction we used Canny's edge. To improve the efficiency of the proposed system we assign different weights by multiplying the features vector by the weight factor generated with the precision process and calculate the similarity between the query image feature vectors and the feature vectors of the image in the database by using Euclidean distance. Experimental results show that the proposed method has higher retrieval accuracy than other conventional methods which combine these three features without the Re-weighting process mentioned above.