S. S. Bukhari, T. Breuel, Abedelkadir Asi, Jihad El-Sana
{"title":"使用机器学习的阿拉伯历史文献图像布局分析","authors":"S. S. Bukhari, T. Breuel, Abedelkadir Asi, Jihad El-Sana","doi":"10.1109/ICFHR.2012.227","DOIUrl":null,"url":null,"abstract":"Page layout analysis is a fundamental step of any document image understanding system. We introduce an approach that segments text appearing in page margins (a.k.a side-notes text) from manuscripts with complex layout format. Simple and discriminative features are extracted in a connected-component level and subsequently robust feature vectors are generated. Multilayer perception classifier is exploited to classify connected components to the relevant class of text. A voting scheme is then applied to refine the resulting segmentation and produce the final classification. In contrast to state-of-the-art segmentation approaches, this method is independent of block segmentation, as well as pixel level analysis. The proposed method has been trained and tested on a dataset that contains a variety of complex side-notes layout formats, achieving a segmentation accuracy of about 95%.","PeriodicalId":291062,"journal":{"name":"2012 International Conference on Frontiers in Handwriting Recognition","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"68","resultStr":"{\"title\":\"Layout Analysis for Arabic Historical Document Images Using Machine Learning\",\"authors\":\"S. S. Bukhari, T. Breuel, Abedelkadir Asi, Jihad El-Sana\",\"doi\":\"10.1109/ICFHR.2012.227\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Page layout analysis is a fundamental step of any document image understanding system. We introduce an approach that segments text appearing in page margins (a.k.a side-notes text) from manuscripts with complex layout format. Simple and discriminative features are extracted in a connected-component level and subsequently robust feature vectors are generated. Multilayer perception classifier is exploited to classify connected components to the relevant class of text. A voting scheme is then applied to refine the resulting segmentation and produce the final classification. In contrast to state-of-the-art segmentation approaches, this method is independent of block segmentation, as well as pixel level analysis. The proposed method has been trained and tested on a dataset that contains a variety of complex side-notes layout formats, achieving a segmentation accuracy of about 95%.\",\"PeriodicalId\":291062,\"journal\":{\"name\":\"2012 International Conference on Frontiers in Handwriting Recognition\",\"volume\":\"37 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"68\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2012 International Conference on Frontiers in Handwriting Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICFHR.2012.227\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 International Conference on Frontiers in Handwriting Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICFHR.2012.227","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Layout Analysis for Arabic Historical Document Images Using Machine Learning
Page layout analysis is a fundamental step of any document image understanding system. We introduce an approach that segments text appearing in page margins (a.k.a side-notes text) from manuscripts with complex layout format. Simple and discriminative features are extracted in a connected-component level and subsequently robust feature vectors are generated. Multilayer perception classifier is exploited to classify connected components to the relevant class of text. A voting scheme is then applied to refine the resulting segmentation and produce the final classification. In contrast to state-of-the-art segmentation approaches, this method is independent of block segmentation, as well as pixel level analysis. The proposed method has been trained and tested on a dataset that contains a variety of complex side-notes layout formats, achieving a segmentation accuracy of about 95%.