期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2017
卷号：6
期号：6
页码：12061
DOI：10.15680/IJIRSET.2017.0606266
出版社：S&S Publications
摘要：Image retrieval is a poor stepchild to other forms of information retrieval (IR). Image retrieval has beenone of the most interesting and research areas in the field of computer vision over the last few decades. Content-BasedImage Retrieval (CBIR) systems are used in order to automatically index, search, retrieve, and browse image databases.Color and texture features are important properties in content-based image retrieval systems. In this paper we havementioned detailed classification of CBIR system. We have defined different techniques as well as the combinations ofthem to improve the performance. We have also defined the effect of different matching techniques on the retrievalprocess.Most content-based image retrievals (CBIR) use color as image features. However, image retrieval using color featuresoften gives disappointing results because in many cases, images with similar colors do not have similar content. Colormethods incorporating spatial information have been proposed to solve this problem; however, these methods oftenresult in very high dimensions of features which drastically slow down the retrieval speed. In this paper, amethodcombining both color and texture features of image is proposed to improve the retrieval performance. Given aquery, images in the database are firstly ranked using color features. Then the top ranked images are re-rankedaccording to their texturefeatures.
关键词：Color; Feature Extraction; Image Retrieval; Texture; SVM etc.
