基于负样本精简概念格规则的语义概念检测.pdfVIP

2011 年 12 月 计算机工程 第37 卷第23 期 Vo 1.37 NO.23 Computer Engineering December 2011 文章编号. 100• 3428(20 1l)23--0054• 3 文献标识码:A 中团分类号， TP3 1l ·软件技术与数据库· 基于负样本精简概念格规则的语义概念检测 漏洞华，禽永脯 (江苏大学计算机科学与通信工程学院，江苏镇江 212013) 摘 要:为挖掘视频中丰富的语义信息，提出某于负样本精简概念格规则的语义概念检测方法。分析基于概念格的语义分析系统，考虑训 练数据中负样本的信息，提出利用负样本精筒的语义规则提取算法，将其应用于视频语义检测。先将视频镜头的低层特征映射到低层语义 特征，再利用该算法生成语义分类规则，进行视频语义概念检测。实验结果表明，该方法是奇效可行的。 关键词:概念格;视频语义概念检测;精简规则;低层语义特征; k-均值 Semantic Concept Detection ßased on Concept Lattice Rule Reduced by Negative Sample PAN Run-hua ,ZHAN Yong-zhao (School of Computer Science and Telecommunication Engineering , Jiangsu University , Zhenjiang 212013 , China) (Abstract) To mine 出e rich semantic information in videos , this paper pro伊ses a semantic concept detection method based on concept lattice rules reduced by negative samples. 币lrough analyzing the semantic analysis system based on concept lattice and considering the information of negative samples in training data, it designs an algorithm for extracting semantic rules reduced by negative s创nples and apples 也e algorit趾n in video semantic detection.τbe low-Ievel features of the video shots are mapped to the low-Ievel semantic features , and the video semantic concept is detected after the semantic classification rules are generated by the proposed me曲。d.E且pèrimental results show the feasibility 缸ld validity of the me由。d. (Key words) concept lattice; video semantic concept detection; reduced rule; low-level semantic feature; k-means DOI: IO.3969/j .issn.IOOO-3428.2011.23.018 1 概述 如简单的运