An Improved Deep Neural Network Based on a Novel Visual Attention Mechanism for Text Recognition

Nguyen Trong Thai, Nguyen Hoang Thuan, D. V. Sang
{"title":"An Improved Deep Neural Network Based on a Novel Visual Attention Mechanism for Text Recognition","authors":"Nguyen Trong Thai, Nguyen Hoang Thuan, D. V. Sang","doi":"10.1109/RIVF51545.2021.9642119","DOIUrl":null,"url":null,"abstract":"Text recognition from images captured by handheld mobile devices has attracted considerable research interest because of its commercial applications. The state-of-the-art printed text recognition methods are often based on attention mechanisms. However, these methods perform poorly on images captured due to poor illumination conditions, blur, noise, and low resolution. To address these unfavorable conditions, we propose a new text recognition method based on an encoder-decoder model. Particularly, we present a novel attention mechanism using a multi-scale cascade fashion combined with a channel attention gate module. Our model is also strengthened by an EfficientNet-like backbone. Extensive experiments on three popular datasets, including SROIE 2019, B-MOD, and CORD, show that our proposed method outperforms the baseline attention mechanism and achieves competitive accuracy compared to other state-ofthe-art approaches.","PeriodicalId":6860,"journal":{"name":"2021 RIVF International Conference on Computing and Communication Technologies (RIVF)","volume":"1 1","pages":"1-6"},"PeriodicalIF":0.0000,"publicationDate":"2021-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 RIVF International Conference on Computing and Communication Technologies (RIVF)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/RIVF51545.2021.9642119","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Text recognition from images captured by handheld mobile devices has attracted considerable research interest because of its commercial applications. The state-of-the-art printed text recognition methods are often based on attention mechanisms. However, these methods perform poorly on images captured due to poor illumination conditions, blur, noise, and low resolution. To address these unfavorable conditions, we propose a new text recognition method based on an encoder-decoder model. Particularly, we present a novel attention mechanism using a multi-scale cascade fashion combined with a channel attention gate module. Our model is also strengthened by an EfficientNet-like backbone. Extensive experiments on three popular datasets, including SROIE 2019, B-MOD, and CORD, show that our proposed method outperforms the baseline attention mechanism and achieves competitive accuracy compared to other state-ofthe-art approaches.
基于视觉注意机制的文本识别改进深度神经网络
从手持移动设备捕获的图像中进行文本识别由于其商业应用而引起了相当大的研究兴趣。最先进的印刷文本识别方法通常是基于注意机制的。然而,由于光照条件差、模糊、噪声和低分辨率,这些方法在捕获图像时表现不佳。为了解决这些不利条件,我们提出了一种新的基于编码器-解码器模型的文本识别方法。特别地,我们提出了一种新的注意机制,使用多尺度级联方式结合通道注意门模块。我们的模型还通过一个类似于efficientnet的主干得到了加强。在SROIE 2019、B-MOD和CORD等三个流行数据集上进行的大量实验表明,与其他最先进的方法相比,我们提出的方法优于基线注意力机制,并实现了具有竞争力的准确性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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:481959085
Book学术官方微信