Automatic figure classification in bioscience literature.

Automatic figure classification in bioscience literature.
复制标题

DOI:
10.1016/j.jbi.2011.05.003
复制
发表时间:
2011-10
影响因子:
4.5
通讯作者:
Yu, Hong
Yu, Hong
中科院分区:
医学3区
文献类型:
--
作者:
Kim, Daehyun;Ramesh, Balaji Polepalli;Yu, Hong

文献摘要

参考文献

被引文献

相似文献

生物医学文章中出现了数以百万计的数字,开发一个智能的数字搜索引擎来根据用户输入返回相关的数字是很重要的。在这项研究中,我们报告了一个数字分类器,自动分类生物医学数字到五个预定义的图形类型:凝胶图像,图像的东西,图形,模型和混合。该分类器挖掘了丰富的图像特征,并将其与文本特征相结合。我们进行了特征选择并探索了不同的分类模型,包括基于规则的图形分类器,监督机器学习分类器和多模型分类器,后者集成了前两个分类器。我们的研究结果表明,特征选择改进了图形分类,我们探索的新图像特征是我们研究过的图像特征中最好的。我们的研究结果还表明,整合文本和图像特征比单独使用它们中的任何一个都能获得更好的性能。最好的系统是一个多模型分类器,它结合了基于规则的层次分类器和支持向量机(SVM)的分类器,实现了76.7%的F1分数为五种类型的分类。我们在http://figureclassification.askhermes.org/上演示了我们的系统。
Millions of figures appear in biomedical articles, and it is important to develop an intelligent figure search engine to return relevant figures based on user entries. In this study we report a figure classifier that automatically classifies biomedical figures into five predefined figure types: Gel-image, Image-of-thing, Graph, Model, and Mix. The classifier explored rich image features and integrated them with text features. We performed feature selection and explored different classification models, including a rule-based figure classifier, a supervised machine-learning classifier, and a multi-model classifier, the latter of which integrated the first two classifiers. Our results show that feature selection improved figure classification and the novel image features we explored were the best among image features that we have examined. Our results also show that integrating text and image features achieved better performance than using either of them individually. The best system is a multi-model classifier which combines the rule-based hierarchical classifier and a support vector machine (SVM) based classifier, achieving a 76.7% F1-score for five-type classification. We demonstrated our system at http://figureclassification.askhermes.org/.
DOI: 10.1093/bioinformatics/btm301
发表时间: 2007-08-15
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Hearst, Marti A.;Divoli, Anna;Ye, Jerry
通讯作者: Ye, Jerry
DOI: 10.1016/0031-3203(91)90143-s
发表时间: 1991-01-01
影响因子: 8
作者:
JAIN, AK;FARROKHNIA, F
通讯作者: FARROKHNIA, F
DOI: 10.1016/s0031-3203(97)00131-3
发表时间: 1998-09-01
影响因子: 8
作者:
Jain, AK;Vailaya, A
通讯作者: Vailaya, A
DOI: 10.1162/089976601750264965
发表时间: 2001-07-01
期刊: NEURAL COMPUTATION
影响因子: 2.9
作者:
Schölkopf, B;Platt, JC;Williamson, RC
通讯作者: Williamson, RC
DOI: 10.1177/001316446002000104
发表时间: 1960-01-01
影响因子: 2.7
作者:
COHEN, J
通讯作者: COHEN, J