期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2013
卷号：4
期号：2
页码：319-323
出版社：TechScience Publications
摘要：In recent years the relevance feedback technology is regarded in content based image retrieval. The idea is to adopt the system to the specific user preferences making more important weights or features that reflect the actual user need in order to achieve higher precision. Therefore we can define relevance feedback as the process by which human and computer interact in order to automatically adjust the query to the real user preferences. The idea is to adjust the query selection criteria to better approximate real user need using the result retrieved by the original query. To be more profitable, relevance feedback techniques were incorporated into CBIR such that more precise result can be obtained by taking users feedback into account.
