中文摘要：

近年来,利用在线文献构建生物数据库引起越来越多的关注,包括论文中生物数据的自动收集、组织和分析。在线文献中图像形式表示的数据具有特别重要的意义。利用在线生物文献中的图像和图像标注,构建在线生物文献核磁共振（MRI）图像库,其中识别文献中的MRI图像是重要的一步。作为从在线文献中构建MRI图像库的必要部分,综合利用图像信息和图像文本标注信息,采用后验相乘、特征拼接和协同学习3种方法来识别文献中的MRI图像。实验表明,综合利用图像和文本两类信息训练得到的分类器,比基于单种信息训练得到的分类器具有更高的识别精度,为构建能解释在线文献中MRI图像的知识系统这一长期目标提供了基础支持。

英文摘要：

Recently,building biological databases from online literature has attracted more attentions,which includes automating the collection,organization and analysis of biological data in the research literature.Images,as an important type of data in online literature,present great significance.It is necessary to build a magnetic resonance imaging（MRI） database that extracts information regarding images and texts in online biological literature.In this paper,MRI image recognition was studied.For better comprehensive utilization of image and text features,we propose three fusion approaches,including merging both features,multiplying both posterior probabilities and Co-training algorithm.Experimental results show a significant improvement in the average accuracy of the three fusion classifiers as compared with classifiers only based on image or text features.