EXTRAFOR automatic EXTRAction of mathematical FORmulas.pdfVIP

下载本文档

6
0
约3.54万字
约 20页
2017-04-11 发布于江苏
举报
版权申诉

EXTRAFOR automatic EXTRAction of mathematical FORmulas.pdf

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

EXTRAFOR automatic EXTRAction of mathematical FORmulas

1EXTRAFOR : Automatic Extraction of Mathematical Formulas 1A. Kacem, A. Bela?d2 and M. Ben Ahmed3 1ENSI-RIADI, 77 Rue de Carthage, Cité Mohamed Ali 2040 Radès Tunisie E-mail : afef.kacem@isg.rnu.tn Tel : (216) 1 444 897 2 LORIA-CNRS, Campus Scientifique, B.P. 239 F-54506 Vandoeuvre-lès-Nancy Cedex France E-mail : abelaid@loria.fr Tel : (33) 03 83 59 20 82 Fax : (33) 03 83 41 30 79 3 ENSI-RIADI, Bo?te postale 275, Cité Mehrajène 1082 Tunis Tunisie E-mail : mohamed.benahmed.serst.rnrt.tn 2EXTRAFOR : Automatic Extraction of Mathematical Formulas Abstract A method for automatic extraction of mathematical formulas from document images without character recognition is described. This method operates into several steps. First, significant symbols of the formula are labeled. Second, this labeling is extended to adjoining symbols by using contextual. Finally, the formula is extracted from the surrounding text by applying some syntactic rules. The primary labeling is realized by models created at a learning step, using fuzzy logic. The average rate of preliminary labeling rate is about 95.3%. 90% of mathematical formulas are well extracted from documents printed with a high quality. Keywords Document segmentation, Mathematical formula labeling, Fuzzy logic, Document segmentation, Contextual and syntactic analysis. 3I. Introduction A document may contain various kinds of components, such as text, image, graphics, and mathematical formulas. Most image analysis systems cannot handle in the same time all these kinds of components. In fact, these components, having different structures and typographies, need to be separated in order to be analyzed more efficiently by dedicated systems. This paper intends to present a system which will separate formulas from the others components of the document. In fact, there is a wealth of mathematical knowledge that can be potentially very useful in many computational applications. But this material is not available in electronic form.