基于几何模型和投影的倾斜校正算法及草书词识别的上行/下行点提取

2007 International Conference on Signal Processing, Communications and Networking Pub Date : 2007-11-05 DOI:10.1109/ICSCN.2007.350786

P. Nagabhushan, S. Angadi, B. Anami

{"title":"基于几何模型和投影的倾斜校正算法及草书词识别的上行/下行点提取","authors":"P. Nagabhushan, S. Angadi, B. Anami","doi":"10.1109/ICSCN.2007.350786","DOIUrl":null,"url":null,"abstract":"Cursive word recognition requires tilt correction before extraction of features such as ascenders and descenders. Skew and slant are the two types of tilts found in cursive word images. This paper presents new algorithms for skew and slant correction using geometric model and image projections. A new algorithm for extraction of ascenders/descenders based on fitting top line and base line references using horizontal histogram projection of the image is also presented. The algorithms are tested on a large sample of 'area' name images drawn from postal addresses. The tilt correction algorithms have been tested on a large sample of images and the results are encouraging. The ascenders/descenders are correctly extracted from 87.86% of test images","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"Geometric Model and Projection Based Algorithms for Tilt Correction and Extraction of Acsenders / Descenders for Cursive Word Recognition\",\"authors\":\"P. Nagabhushan, S. Angadi, B. Anami\",\"doi\":\"10.1109/ICSCN.2007.350786\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Cursive word recognition requires tilt correction before extraction of features such as ascenders and descenders. Skew and slant are the two types of tilts found in cursive word images. This paper presents new algorithms for skew and slant correction using geometric model and image projections. A new algorithm for extraction of ascenders/descenders based on fitting top line and base line references using horizontal histogram projection of the image is also presented. The algorithms are tested on a large sample of 'area' name images drawn from postal addresses. The tilt correction algorithms have been tested on a large sample of images and the results are encouraging. The ascenders/descenders are correctly extracted from 87.86% of test images\",\"PeriodicalId\":257948,\"journal\":{\"name\":\"2007 International Conference on Signal Processing, Communications and Networking\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-11-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 International Conference on Signal Processing, Communications and Networking\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSCN.2007.350786\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 International Conference on Signal Processing, Communications and Networking","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSCN.2007.350786","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 11

摘要

草书词识别需要在提取上升和下降等特征之前进行倾斜校正。歪斜和倾斜是草书文字图像中的两种倾斜类型。本文提出了一种利用几何模型和图像投影进行倾斜和倾斜校正的新算法。提出了一种基于图像水平直方图投影拟合顶线和基准线的上升/下降点提取算法。这些算法在从邮政地址中抽取的大量“地区”名称图像样本上进行了测试。倾斜校正算法已经在大量图像样本上进行了测试，结果令人鼓舞。从87.86%的测试图像中正确提取了上升/下降点

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Geometric Model and Projection Based Algorithms for Tilt Correction and Extraction of Acsenders / Descenders for Cursive Word Recognition

Cursive word recognition requires tilt correction before extraction of features such as ascenders and descenders. Skew and slant are the two types of tilts found in cursive word images. This paper presents new algorithms for skew and slant correction using geometric model and image projections. A new algorithm for extraction of ascenders/descenders based on fitting top line and base line references using horizontal histogram projection of the image is also presented. The algorithms are tested on a large sample of 'area' name images drawn from postal addresses. The tilt correction algorithms have been tested on a large sample of images and the results are encouraging. The ascenders/descenders are correctly extracted from 87.86% of test images

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2007 International Conference on Signal Processing, Communications and Networking

自引率

0.00%

发文量