基于内容的Web图像搜索引擎的图像检索算法研究-计算机应用技术专业论文.docx

了比较明显的改善。 关 键 字：基于内容图像搜索引擎；图像特征提取；区域加权信息熵；相关反馈 研究类型：应用研究 Subject :Image Retrieval Algorithms for Content-based Web Image Search Engines Specialty : Computer Application Technology Name : Jing He (Signature) Instructor : Aiguo Li (Signature) ABSTRACT Based on the content of the image search engine (CBIR) is to search images which user wants according to the characteristics from images database. It has very important theoretical significance for content-based search engine that studying on more effective image retrieval technology, since it could improve customer’s satisfaction on the image search engine. This article will use dynamic adjusting the weights area-weighted information entropy algorithm to extract image features. Based on research of relevant feedback, multi-feature fusion relevant feedback algorithm has been achieved. On the basis of image feature extraction and image search engine relevant feedback techniques, explore and research image feature extraction and relevant feedback techniques suitable for content-based image search engine technology, and develop content-based search engine system. The major work includes. Existing image feature extraction algorithms have been analyzed, considering the fixed weights area-weighted information entropy extraction algorithm does not meet the requirements of complex digital image system, on the basis of area-weighted information entropy, the dynamic adjusting the weights area-weighted information entropy has been put forward. Use the dynamic adjusting the weights area-weighted information entropy as the image’s descriptor to indicate the image features, query the source image in the image segmentation based on analysis and research to determine the weights for each region of the image based on image color space distribution, the dynamic adjusting the weights area-weighted information entropy can been achieved. Tests show that the precision rate to extract image features with the dynamic adjusting the weights