Multi-Feature Extraction in Content Based Image Retrieval

چکیده مقاله

Content Based Image Retrieval (CBIR) methods are developing rapidly because of the rising need to access and search distributed digital documents. Feature extraction and representation is one of the most important phases in the CBIR. This paper proposed a new method of image similarity by combination of edge and color feature via bipartite graphs. In order to evaluate the performance of the proposed method "WANG" dataset was considered. The efficiency of proposed method is demonstrated by comparing the results of several state-of-the-arts method of image retrieval approaches. Experimental results show that the proposed method yields higher retrieval accuracy than some existing methods and integration of color and edge information provides a

دریافت لینک دانلود مقاله