基于高层语义的图像检索双方.pdfVIP

1000-9825/2004/15( 10) 1461 ©2004 Journal of Software 软 件 学 报 Vol.15, No.10 基于高层语义的图像检索算法 + 王崇骏, 杨育彬, 陈世福 (南京大学 计算机软件新技术国家重点实验室,江苏 南京 210093) Algorithms of High-Level Semantic-Based Image Retrieval + WANG Chong-Jun , YANG Yu-Bin, CHEN Shi-Fu (National Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093, China) + Corresponding author: Phn: +86-25 E-mail: chjwang_con@163.com, http://www.nju . Received 2003-07-07; Accepted 2004-02-03 Wang CJ, Yang YB, Chen SF. Algorithms of high-level semantic-based image retrieval. Journal of Software, 2004,15(10):1461~1469. /1000-9825/15/ 1461.htm Abstract: IPSM is an integrated probabilistic image semantic description multi-level model. This model includes input layer, feature layer, semantic layer, synthetical probability layer, probability propagation layer, and semantic mapping layer. Based on the model and characterizing of the image high -level semantic content according to Bayesian theory, SHM (semantic high-level retrieval algorithm) and SRF (high -level semantic relevance feedback) for image retrieval based on high-level semantic content, for user relevance feedback respectively, are designed and implemented. Experimental results indicate that IPSM, SHM and SRF are effective in characterizing image high-level semantic content and can provide sound and robust image retrieval performance. Key words: SHM; semantic feature extraction ; Bayesian statistical learning; semantic thesaurus; relevance feedback 摘 要: 利用 Bayes 统计学习和决策理论,建立了一种图像语义综合概率描述模型(image probability semantic model, 简称IPSM).该模型是一种基于描述性特征建模方法的分层体系结构,由原始图像层、图像特征层、图像语义 层、综合概率层、概率传播层和语义映射层6 个部分组成.并在IPSM 模型对图像的语义分类特征进行描述和提取 的基础上,提出并实现了基于高层语义的图像检索算法(semantic high-level retrieval algorithm, 简称SHM) 以及基于 高层语义的相关反馈算法(semantic relevance f