Content Based Image Retrieval System Using Fusion of Texture Features with Various Distance Metrics

computer science engineering

Abstract- From previous few years, the necessity of a large database used to reserve vast images has been developed very fast and will also increase in the coming generation. From the enormous database, extracting and querying of the images perfectly is supreme to produce the visual content. Content Based Image Retrieval System (CBIRS) provides us utmost outcome to fetch the images from massive dataset. In these systems, various features like texture, shape, color, spatial information, edge etc. can be used to represent an image. This paper provides the review of basic features of an image denoted by color, texture and shape. For color feature extraction, techniques like color histogram (CH), dominant color descriptor (DCD), Color correlogram etc. have been described. Tamura, steerable pyramid, Gabor wavelet transform, grey level co-occurrence matrix (GLCM) are the techniques described for texture features extraction and lastly Zernike moments and MPEG-7 for shape feature extraction. If we are using single feature to retrieve the image, it takes more retrieval time. In this paper, a review of Content based retrieval system (CBIRS) is explained.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.