您的位置:首页  > 论文页面

基于文本的科技论文图像检索

发表时间:2009-02-28  浏览量:2110  下载量:975
全部作者: 马德奎,马军,王瑜
作者单位: 山东大学计算机科学与技术学院;重庆农村商业银行
摘 要: 分析了建立科技论文图像检索系统的必要性,并对建立该系统需要解决的两个问题进行了研究。一是提出了一种从科技论文中提取图像的算法。该算法首先将文档转换成文档图像,然后使用颜色直方图、一阶颜色矩、二阶颜色矩等图像底层特征去发现科技论文中的内容图像,使用该方法提取图像可以达到94.3%的准确率。二是提出了基于规则的相关文本提取算法。使用标题、摘要、关键词和周边文本这4种相关文本的不同组合为图像建立索引。实验表明:使用标题和周边文本为图像建立索引检索效果最好。�
关 键 词: 计算机应用;图像检索;图像提取;相关文本;科技论文�
Title: Text based image retrieval on scientific documents database
Author: MA Dekui, MA Jun, WANG Yu
Organization: School of Computer Science and Technology, Shandong University; Chongqing Rural Commercial Bank
Abstract: The necessity of building image retrieval system on scientific documents database is analyzed and two related problems are studied. One is that an image extraction method is proposed to extract images from scientific documents. In this method, the documents are transformed to document images, and then color histogram, one-order color moment and two-order color moment are used to find out content images from document images and a precision value of 94.3% is obtained. The other is that a rule-based related text extraction method is proposed. Different combinations of title, abstract, keywords and surrounding text are used to index the content images. The experiment result shows that using the title and surrounding text to index images results in best retrieval performance. �
Key words: computer application; image retrieval; image extraction; related text; scientific documents
发表期数: 2009年2月第4期
引用格式: 马德奎,马军,王瑜. 基于文本的科技论文图像检索[J]. 中国科技论文在线精品论文,2009,2(4):393-399.
 
2 评论数 0
暂无评论
友情链接