期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：11
出版社：S.S. Mishra
摘要：A content based image retrieval has become very popular system now a days. As previously used text based system founds very tedious and as a difficult task for image retrieval. But the CBIR is the method where there are many methodologies are available and the task of image retrieval becomes effectively easier. Here we use different feature descriptors such as, color ,texture and shape descriptors to represent low level features of image. There are the techniques called a'trous wavelet transform (AWT) and Julesz's texton elements are used to generate the texton image. Also the multi texton histogram (MTH) is one of the method for this task. It integrates the advantages of co -occurrence matrix and histogram by representing the attributes of co -occurrence matrix using histogram. Here, the user directed mechanism for CBIR using an interactive genetic algorithm (IGA) is proposed and implemented. The color attributes like the mean value, standard deviation and image bitmap of a color image are used as a features for retrieval.
