Natural Scene Text Detection Algorithm Based on Improved DBNet

Hui Chen, J. Liu, Weimin Zhou
{"title":"Natural Scene Text Detection Algorithm Based on Improved DBNet","authors":"Hui Chen, J. Liu, Weimin Zhou","doi":"10.1109/ICEICT55736.2022.9909509","DOIUrl":null,"url":null,"abstract":"There are many problems in text detection, such as large scale differences of high-resolution image features and poor multi-scale feature fusion, we propose an improved algorithm based on dbnet. On the basis of the feature fusion module, we add a atrous Convolution network with kernel-shared pooling to increase the receptive field, so that higher-level semantic information can be obtained in the feature fusion network, and through the shared kernel, the number of model parameters can be reduced, the computational cost can be reduced, and the detection accuracy can be improved. At the same time, we add the attention mechanism into the residual network to suppress the complex background noise and promote the information interaction between channels. In the loss function, we use dice loss partially to solve the imbalance of positive and negative sample data. Our experimental evaluation is on ICDAR2013 and ICDAR2015 datasets. The experimental results show that the algorithm has a certain improvement in accuracy and F value.","PeriodicalId":179327,"journal":{"name":"2022 IEEE 5th International Conference on Electronic Information and Communication Technology (ICEICT)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 5th International Conference on Electronic Information and Communication Technology (ICEICT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEICT55736.2022.9909509","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

There are many problems in text detection, such as large scale differences of high-resolution image features and poor multi-scale feature fusion, we propose an improved algorithm based on dbnet. On the basis of the feature fusion module, we add a atrous Convolution network with kernel-shared pooling to increase the receptive field, so that higher-level semantic information can be obtained in the feature fusion network, and through the shared kernel, the number of model parameters can be reduced, the computational cost can be reduced, and the detection accuracy can be improved. At the same time, we add the attention mechanism into the residual network to suppress the complex background noise and promote the information interaction between channels. In the loss function, we use dice loss partially to solve the imbalance of positive and negative sample data. Our experimental evaluation is on ICDAR2013 and ICDAR2015 datasets. The experimental results show that the algorithm has a certain improvement in accuracy and F value.
基于改进DBNet的自然场景文本检测算法
针对文本检测中存在的高分辨率图像特征尺度差异大、多尺度特征融合差等问题,提出了一种基于dbnet的改进算法。在特征融合模块的基础上,我们增加了一个带有核共享池的属性卷积网络来增加接收域,从而在特征融合网络中获得更高层次的语义信息,并且通过共享核减少了模型参数的数量,降低了计算成本,提高了检测精度。同时,在残差网络中加入注意机制,抑制复杂的背景噪声,促进信道间的信息交互。在损失函数中,我们部分使用了骰子损失来解决正负样本数据的不平衡问题。我们的实验评估是基于ICDAR2013和ICDAR2015数据集。实验结果表明,该算法在精度和F值上都有一定的提高。
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:604180095
Book学术官方微信