期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2013
卷号：2
期号：12
页码：3195-3201
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Image retrieval has been popular for several years. This paper propose a generalized query method of content based image retrieval system (CBIR) by using the several features and technique [1] i.e. color, texture, shape and GLCM, and also content based image retrieval system based on the combination of local and global features. The local features used are Bi-directional Empirical Mode Decomposition (BEMD) technique for edge detection and Harris corner detector to detect the corner points of an image. The global feature used is HSV color feature. The results show the CBIR systems performs well in the training and using a query method which increases the system searching ability and also using this combination of color, texture and shape is better as obtaining output with a several feature and technique and significant improvement in the retrieval accuracy.
