水力发电学报
            首 页   |   期刊介绍   |   编委会   |   投稿须知   |   下载中心   |   联系我们   |   学术规范   |   编辑部公告   |   English

水力发电学报 ›› 2024, Vol. 43 ›› Issue (9): 124-136.doi: 10.11660/slfdxb.20240911

• • 上一篇    

水工混凝土材料不可编辑文本智能解译方法研究

  

  • 出版日期:2024-09-25 发布日期:2024-09-25

Intelligent interpretation method for non-editable texts of hydraulic concrete materials

  • Online:2024-09-25 Published:2024-09-25

摘要: 在水电工程建设过程中,产生了大量不可编辑的水工混凝土材料文档,采用人工解译的方法获取文本费时费力且精度不可控,难以满足材料数据信息化管理的需求。为此,本文提出了面向水工混凝土材料不可编辑文本的智能解译方法。首先,构建了基于像素级分割的文本检测模型HC-PSENet,融合PP-HGNet主干网络实现文本行的精确检测。进一步,基于领域知识创建专业语料库以获取字符的准确映射,以检测文本框和专业语料库为输入,建立了水工混凝土材料文本识别模型HC-CRNN,采用ResNet主干网络和改进损失函数C-CTC Loss提高字符分类准确性。最后,以自制数据集为例,引入迁移学习策略训练模型,通过消融、对比实验验证了方法的有效性和优越性。结果表明,本文提出的方法检测文本区域的调和平均数为0.985,识别文本的准确率达到90.62%,综合性能均优于经典方法,以期为混凝土材料不可编辑资源的自动化再利用提供新的技术手段。

关键词: 水工混凝土材料, 文本检测, 文本识别, 深度学习, 领域知识

Abstract: During the construction of a hydropower project, a large number of non-editable documents for hydraulic concrete materials are generated. Using manual interpretation methods to obtain texts is time-consuming, laborious and accuracy-uncontrollable, making it difficult to meet the demand for information management of material data. This paper develops an intelligent interpretation method for non-editable texts of hydraulic concrete materials. First, we construct a text detection model, HC-PSENet, based on pixel level segmentation, which integrates the backbone network of PP-HGNet to achieve accurate detection of text lines. Then, a professional corpus is created based on the domain knowledge to realize accurate character mapping. We construct a text recognition model HC-CRNN for hydraulic concrete materials, using detection text boxes and the professional corpus as its inputs, and adopt the backbone network of ResNet and the improved loss function C-CTC Loss to improve the accuracy of character classification. Finally, a transfer learning strategy is adopted to train the model with the self-designed dataset as an example; the effectiveness and superiority of our new method is verified through ablation and comparative experiments. The results show that it has a harmonic mean of 0.985 for detecting text regions and its accuracy of text recognition reaches 90.62%. It has an overall performance superior to classical methods and would provide new technical means for the automated reuse of non-editable text resources in concrete materials.

Key words: hydraulic concrete materials, text detection, text recognition, deep learning, domain knowledge

京ICP备13015787号-3
版权所有 © 2013《水力发电学报》编辑部
编辑部地址:中国北京清华大学水电工程系 邮政编码:100084 电话:010-62783813
本系统由北京玛格泰克科技发展有限公司设计开发  技术支持:support@magtech.com.cn