Rich Get Richer——图像检索中的一种自适应的相关反馈方法

早期的基于内容的图像检索系统以图像处理技术为核心，研究重点集中在视觉特征的选择和提取方面，而没有充分利用人们在视觉方面的主观性和人类所广泛使用的高层次概念和低层次视觉特征之间的相关性。为解决上述问题，近年来相关反馈在基于内容的图像检索中受到重视。提出了一种新的相关反馈方法，使得高层次语义特征能够逐步嵌入到基于 低层次特征的图像检索中，该方法不仅能够记忆以前的交互信息，而且能够记忆相应的交互信息给系统带来的影响，实验结果表明该方法准确率高、响应速度快。

RICH GET RICHER-AN ADAPTIVE RELEVANCE FEEDBACK APPROACH FOR CONTENT-BASED IMAGE RETRIEVAL

Content based image retrieval(CBIR) has become one of the most active research areas in the past few years. At the early stage of CBIR, research primarily focused on exploring various feature representations, and ignored the subjectivity of human perception. There exists a gap between high level concepts and low level features. Relevance feedback is a promising approach to finding a mapping between semantic objects and low level features. A novel relevance feedback approach for image retrieval, the Rich Get Richer (RGR) strategy, is proposed in this paper. It is based on the general framework of Bayesian inference in statistics. The user's feedback information is propagated into the retrieval process step by step. With the Rich Get Richer (RGR) strategy, the more promising images are emphasized. On the contrary, the less promising ones are de emphasized. The experimental results show that the proposed approach greatly reduces the user's efforts of composing a query, and captures the needed information for the user more precisely.