Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition最新文献
Pub Date : 2017-11-01Epub Date: 2018-01-29DOI: 10.1109/ICDAR.2017.210
Siyang Qin, Roberto Manduchi
We introduce an algorithm for word-level text spotting that is able to accurately and reliably determine the bounding regions of individual words of text "in the wild". Our system is formed by the cascade of two convolutional neural networks. The first network is fully convolutional and is in charge of detecting areas containing text. This results in a very reliable but possibly inaccurate segmentation of the input image. The second network (inspired by the popular YOLO architecture) analyzes each segment produced in the first stage, and predicts oriented rectangular regions containing individual words. No post-processing (e.g. text line grouping) is necessary. With execution time of 450 ms for a 1000 × 560 image on a Titan X GPU, our system achieves good performance on the ICDAR 2013, 2015 benchmarks [2], [1].
{"title":"Cascaded Segmentation-Detection Networks for Word-Level Text Spotting.","authors":"Siyang Qin, Roberto Manduchi","doi":"10.1109/ICDAR.2017.210","DOIUrl":"10.1109/ICDAR.2017.210","url":null,"abstract":"<p><p>We introduce an algorithm for word-level text spotting that is able to accurately and reliably determine the bounding regions of individual words of text \"in the wild\". Our system is formed by the cascade of two convolutional neural networks. The first network is fully convolutional and is in charge of detecting areas containing text. This results in a very reliable but possibly inaccurate segmentation of the input image. The second network (inspired by the popular YOLO architecture) analyzes each segment produced in the first stage, and predicts oriented rectangular regions containing individual words. No post-processing (e.g. text line grouping) is necessary. With execution time of 450 ms for a 1000 × 560 image on a Titan X GPU, our system achieves good performance on the ICDAR 2013, 2015 benchmarks [2], [1].</p>","PeriodicalId":90689,"journal":{"name":"Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition","volume":"2017 ","pages":"1275-1282"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5858575/pdf/nihms904003.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35934606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we propose a novel algorithm, based on stroke components and descriptive Gabor filters, to detect text regions in natural scene images. Text characters and strings are constructed by stroke components as basic units. Gabor filters are used to describe and analyze the stroke components in text characters or strings. We define a suitability measurement to analyze the confidence of Gabor filters in describing stroke component and the suitability of Gabor filters on an image window. From the training set, we compute a set of Gabor filters that can describe principle stroke components of text by their parameters. Then a K -means algorithm is applied to cluster the descriptive Gabor filters. The clustering centers are defined as Stroke Gabor Words (SGWs) to provide a universal description of stroke components. By suitability evaluation on positive and negative training samples respectively, each SGW generates a pair of characteristic distributions of suitability measurements. On a testing natural scene image, heuristic layout analysis is applied first to extract candidate image windows. Then we compute the principle SGWs for each image window to describe its principle stroke components. Characteristic distributions generated by principle SGWs are used to classify text or nontext windows. Experimental results on benchmark datasets demonstrate that our algorithm can handle complex backgrounds and variant text patterns (font, color, scale, etc.).
{"title":"Text Detection in Natural Scene Images by Stroke Gabor Words.","authors":"Chucai Yi, Yingli Tian","doi":"10.1109/ICDAR.2011.44","DOIUrl":"https://doi.org/10.1109/ICDAR.2011.44","url":null,"abstract":"<p><p>In this paper, we propose a novel algorithm, based on stroke components and descriptive Gabor filters, to detect text regions in natural scene images. Text characters and strings are constructed by stroke components as basic units. Gabor filters are used to describe and analyze the stroke components in text characters or strings. We define a suitability measurement to analyze the confidence of Gabor filters in describing stroke component and the suitability of Gabor filters on an image window. From the training set, we compute a set of Gabor filters that can describe principle stroke components of text by their parameters. Then a <i>K</i> -means algorithm is applied to cluster the descriptive Gabor filters. The clustering centers are defined as Stroke Gabor Words (SGWs) to provide a universal description of stroke components. By suitability evaluation on positive and negative training samples respectively, each SGW generates a pair of characteristic distributions of suitability measurements. On a testing natural scene image, heuristic layout analysis is applied first to extract candidate image windows. Then we compute the principle SGWs for each image window to describe its principle stroke components. Characteristic distributions generated by principle SGWs are used to classify text or nontext windows. Experimental results on benchmark datasets demonstrate that our algorithm can handle complex backgrounds and variant text patterns (font, color, scale, etc.).</p>","PeriodicalId":90689,"journal":{"name":"Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition","volume":"2011 ","pages":"177-181"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/ICDAR.2011.44","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"32722378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-01DOI: 10.1007/s10032-004-0127-2
V. Eglin, S. Bres
{"title":"Analysis and interpretation of visual saliency for document functional labeling","authors":"V. Eglin, S. Bres","doi":"10.1007/s10032-004-0127-2","DOIUrl":"https://doi.org/10.1007/s10032-004-0127-2","url":null,"abstract":"","PeriodicalId":90689,"journal":{"name":"Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition","volume":"30 1","pages":"28-43"},"PeriodicalIF":0.0,"publicationDate":"2004-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75648754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-01DOI: 10.1007/s10032-004-0125-4
M. Nakagawa, Kaoru Matsumoto
{"title":"Collection of on-line handwritten Japanese character pattern databases and their analyses","authors":"M. Nakagawa, Kaoru Matsumoto","doi":"10.1007/s10032-004-0125-4","DOIUrl":"https://doi.org/10.1007/s10032-004-0125-4","url":null,"abstract":"","PeriodicalId":90689,"journal":{"name":"Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition","volume":"11968 1","pages":"69-81"},"PeriodicalIF":0.0,"publicationDate":"2004-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86219267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-01DOI: 10.1007/s10032-004-0120-9
R. Zanibbi, D. Blostein, J. Cordy
{"title":"A survey of table recognition","authors":"R. Zanibbi, D. Blostein, J. Cordy","doi":"10.1007/s10032-004-0120-9","DOIUrl":"https://doi.org/10.1007/s10032-004-0120-9","url":null,"abstract":"","PeriodicalId":90689,"journal":{"name":"Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition","volume":"1 1","pages":"1-16"},"PeriodicalIF":0.0,"publicationDate":"2004-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73975534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-01DOI: 10.1007/s10032-004-0121-8
A. Tonazzini, L. Bedini, E. Salerno
{"title":"Independent component analysis for document restoration","authors":"A. Tonazzini, L. Bedini, E. Salerno","doi":"10.1007/s10032-004-0121-8","DOIUrl":"https://doi.org/10.1007/s10032-004-0121-8","url":null,"abstract":"","PeriodicalId":90689,"journal":{"name":"Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition","volume":"104 1","pages":"17-27"},"PeriodicalIF":0.0,"publicationDate":"2004-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79163592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-03-01DOI: 10.1007/s10032-004-0128-1
Jean-Baptiste Fasquel, M. Bruynooghe
{"title":"A hybrid opto-electronic method for fast off-line handwritten signature verification","authors":"Jean-Baptiste Fasquel, M. Bruynooghe","doi":"10.1007/s10032-004-0128-1","DOIUrl":"https://doi.org/10.1007/s10032-004-0128-1","url":null,"abstract":"","PeriodicalId":90689,"journal":{"name":"Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition","volume":"19 1","pages":"56-68"},"PeriodicalIF":0.0,"publicationDate":"2004-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82530020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-01DOI: 10.1007/s10032-003-0107-y
Stefan Jäger, Cheng-Lin Liu, M. Nakagawa
{"title":"The state of the art in Japanese online handwriting recognition compared to techniques in western handwriting recognition","authors":"Stefan Jäger, Cheng-Lin Liu, M. Nakagawa","doi":"10.1007/s10032-003-0107-y","DOIUrl":"https://doi.org/10.1007/s10032-003-0107-y","url":null,"abstract":"","PeriodicalId":90689,"journal":{"name":"Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition","volume":"35 1","pages":"75-88"},"PeriodicalIF":0.0,"publicationDate":"2003-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86924636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-01DOI: 10.1007/s10032-002-0084-6
F. Cesarini, E. Francesconi, M. Gori, G. Soda
{"title":"Analysis and understanding of multi-class invoices","authors":"F. Cesarini, E. Francesconi, M. Gori, G. Soda","doi":"10.1007/s10032-002-0084-6","DOIUrl":"https://doi.org/10.1007/s10032-002-0084-6","url":null,"abstract":"","PeriodicalId":90689,"journal":{"name":"Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition","volume":"98 1","pages":"102-114"},"PeriodicalIF":0.0,"publicationDate":"2003-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76493568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-01DOI: 10.1007/s10032-003-0113-0
Alessandro Lameiras Koerich, R. Sabourin, C. Suen
{"title":"Lexicon-driven HMM decoding for large vocabulary handwriting recognition with multiple character models","authors":"Alessandro Lameiras Koerich, R. Sabourin, C. Suen","doi":"10.1007/s10032-003-0113-0","DOIUrl":"https://doi.org/10.1007/s10032-003-0113-0","url":null,"abstract":"","PeriodicalId":90689,"journal":{"name":"Proceedings of the ... International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition","volume":"39 1","pages":"126-144"},"PeriodicalIF":0.0,"publicationDate":"2003-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84305321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号