发布求助
文献互助 智能选刊 最新文献

2014 11th IAPR International Workshop on Document Analysis Systems最新文献

筛选
英文 中文
Curriculum Learning for Handwritten Text Line Recognition 手写体文本行识别课程学习
2014 11th IAPR International Workshop on Document Analysis Systems Pub Date : 2013-12-05 DOI: 10.1109/DAS.2014.38
J. Louradour, Christopher Kermorvant
{"title":"Curriculum Learning for Handwritten Text Line Recognition","authors":"J. Louradour, Christopher Kermorvant","doi":"10.1109/DAS.2014.38","DOIUrl":"https://doi.org/10.1109/DAS.2014.38","url":null,"abstract":"Recurrent Neural Networks (RNN) have recently achieved the best performance in off-line Handwriting Text Recognition. At the same time, learning RNN by gradient descent leads to slow convergence, and training times are particularly long when the training database consists of full lines of text. In this paper, we propose an easy way to accelerate stochastic gradient descent in this set-up, and in the general context of learning to recognize sequences. The principle is called Curriculum Learning, or shaping. The idea is to first learn to recognize short sequences before training on all available training sequences. Experiments on three different handwritten text databases (Rimes, IAM, OpenHaRT) show that a simple implementation of this strategy can significantly speed up the training of RNN for Text Recognition, and even significantly improve performance in some cases.","PeriodicalId":220495,"journal":{"name":"2014 11th IAPR International Workshop on Document Analysis Systems","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115551546","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}
引用次数: 21
Multiclass Learning for Writer Identification Using Error-Correcting Codes 基于纠错码的作家识别多班学习
2014 11th IAPR International Workshop on Document Analysis Systems Pub Date : 2013-10-01 DOI: 10.1109/DAS.2014.73
U. Porwal, Chetan Ramaiah, Ashish Kumar, V. Govindaraju
{"title":"Multiclass Learning for Writer Identification Using Error-Correcting Codes","authors":"U. Porwal, Chetan Ramaiah, Ashish Kumar, V. Govindaraju","doi":"10.1109/DAS.2014.73","DOIUrl":"https://doi.org/10.1109/DAS.2014.73","url":null,"abstract":"Writer Identification can be seen as a multi-class learning problem where number of writers are different classes. One of the fundamental approaches to solve a multi-class problemis by breaking it into binary classification tasks. In this work weare proposing a generic approach for multi-class classification using an ensemble of binary classifiers. We assign a distributedoutput representation to each class in the form of codewords andan ensemble of binary classifiers is created where each classifierpredicts one bit of the codeword. Actual label is determined using Belief Propagation algorithm on a graph constructed from the code matrix. We have performed experiments on a new publiclyavailable IBM-UB-1 dataset for the task of writer identification to show the efficacy of our method.","PeriodicalId":220495,"journal":{"name":"2014 11th IAPR International Workshop on Document Analysis Systems","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132368258","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}
引用次数: 1
Sequential Word Spotting in Historical Handwritten Documents 历史手写体文件中的顺序词识别
2014 11th IAPR International Workshop on Document Analysis Systems Pub Date : 1900-01-01 DOI: 10.1109/DAS.2014.18
D. F. Mota, R. Manmatha, A. Fornés, J. Lladós
{"title":"Sequential Word Spotting in Historical Handwritten Documents","authors":"D. F. Mota, R. Manmatha, A. Fornés, J. Lladós","doi":"10.1109/DAS.2014.18","DOIUrl":"https://doi.org/10.1109/DAS.2014.18","url":null,"abstract":"In this work we present a handwritten word spotting approach that takes advantage of the a priori known order of appearance of the query words. Given an ordered sequence of query word instances, the proposed approach performs a sequence alignment with the words in the target collection. Although the alignment is quite sparse, i.e. the number of words in the database is higher than the query set, the improvement in the overall performance is sensitively higher than isolated word spotting. As application dataset, we use a collection of handwritten marriage licenses taking advantage of the ordered index pages of family names.","PeriodicalId":220495,"journal":{"name":"2014 11th IAPR International Workshop on Document Analysis Systems","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121502371","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}
引用次数: 7
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信