基于视觉感知的图像检索的研究  

A Survey of Image Retrieval Based on Visual Perception

作　　者：张菁[1] 沈兰荪[1] David Dagan Feng 

机构地区：[1]北京工业大学信号与信息处理研究室,北京100022 [2]悉尼大学信息学院,澳大利亚悉尼2006 [3]香港理工大学电子与资讯工程学系,中国香港

出　　处：《电子学报》2008年第3期494-499,共6页Acta Electronica Sinica

基　　金：国家自然科学基金(No.60472036,No.60431020,No.60402036);教育部博士点基金(No.20040005015);北京市自然科学基金(No.3052005);the PolyU/UGC grants(No.B-Q698)

摘　　要：基于内容图像检索的一个突出问题是图像低层特征与高层语义之间存在的巨大鸿沟.针对相关反馈和感兴趣区检测在弥补语义鸿沟时存在主观性强、耗时的缺点,提出了视觉信息是一种客观反映图像高层语义的新特征,基于视觉信息进行图像检索可以有效减小语义鸿沟;并在总结视觉感知的研究进展和实现方法的基础上,给出了基于视觉感知的图像检索在感兴趣区检测、图像分割、相关反馈和个性化检索四个方面的研究思路.One of the most challenging research issues in content-based image retrieval （CBIR） is how to bridge the significant semantic gap between the low-level image features and the high-level semantic concepts. The well-known solutions are rele-vance feedback and regions of interest （ROls） detection;however both are subjective and time-consuming. We propose the visual information is a new feature that can objectively interpret the high-level concepts and effectively reduce the semantic gap in image retrieval. We also make a survey on the research progresses and key technologies of visual perception. The research issues of image retrieval based on visual perception are introduced as well from four aspects： ROIs detection, image segmentation, relevance feedback and personalized retrieval.

关 键 词：视觉感知 图像检索 语义鸿沟 感兴趣区 相关反馈 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]