一种基于深度学习的PCB图像字符检测方法

doi:10.13190/j.jbupt.2021-109

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (1): 108-114.doi: 10.13190/j.jbupt.2021-109

一种基于深度学习的PCB图像字符检测方法

张滨宇, 赵衍运, 杜昀昊, 万俊峰, 佟知航

北京邮电大学人工智能学院, 北京 100876

收稿日期:2021-06-11 出版日期:2022-02-28 发布日期:2021-12-16
作者简介:张滨宇(1998—),男,硕士生,邮箱:zhangbinyu@bupt.edu.cn;赵衍运(1964—),女,硕士生导师
基金资助:
国家重点研发计划项目（2017YFC0803804）

Character Detection Method for PCB Image Based on Deep Learning

ZHANG Binyu, ZHAO Yanyun, DU Yunhao, WAN Junfeng, TONG Zhihang

School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2021-06-11 Online:2022-02-28 Published:2021-12-16

摘要/Abstract

摘要： 利用印刷电路板（PCB）残片图像的字符检索完整PCB图像，是解决PCB残片溯源难题的一种有效方法；为此，提出了一种高性能的PCB图像字符检测方法。基于残差网络结构实现特征金字塔的提取，设计双检测头进行字符区域预测，引入结构相似性损失函数优化网络；设计了一种适合PCB图像的字符区域热力图标签生成算法以训练网络；采用多种数据增强、多尺度检测等策略提高字符检测性能。在自建PCB图像数据集上进行测试，该方法的字符检测精准率为95.6%、召回率为92.4%；特别是综合指标F1为93.6%，优于对比方法，证明了针对PCB图像字符检测问题，所提出的综合检测方法可与当前自然场景图像字符检测的先进方法媲美。

关键词: 印刷电路板图像, 字符检测, 深度学习

Abstract: Retrieve the printed circuit board (PCB) image with characters is an effective method for PCB fragments tracing. To this end, a high-performance character detection method for PCB images is proposed, which adopts feature pyramid network based on residual network and has two detecting heads to predict character distribution heatmaps. The local pattern consistency loss function is introduced to optimize the network model. A heatmap generation algorithm of character region for network training is presented. A series of strategies are adopted, such as data augmentation and multi-scale detection, which increases the performance of character detection. The test results on PCB image set show that the character detection accuracy is 95.6% and the recall rate is 92.4%. Especially, F1 score can reach 93.6%, which exceeds the comparison methods, proving that the proposed comprehensive detection method outperforms the state of the art methods of character detection in natural scene images.

Key words: printed circuit board image, character detection, deep learning

中图分类号:

TP391.4

张滨宇, 赵衍运, 杜昀昊, 万俊峰, 佟知航. 一种基于深度学习的PCB图像字符检测方法[J]. 北京邮电大学学报, 2022, 45(1): 108-114.

ZHANG Binyu, ZHAO Yanyun, DU Yunhao, WAN Junfeng, TONG Zhihang. Character Detection Method for PCB Image Based on Deep Learning[J]. Journal of Beijing University of Posts and Telecommunications, 2022, 45(1): 108-114.

参考文献

[1] XING L J, TIAN Z, HUANG W L, et al. Convolutional character networks[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul:IEEE, 2019:9126-9136.
[2] ZHOU X Y, YAO C, WEN H, et al. East:an efficient and accurate scene text detector[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii:IEEE, 2017:5551-5560.
[3] LONG S B, RUAN J Q, ZHANG W J, et al. Textsnake:a flexible representation for detecting text of arbitrary shapes[C]//Proceedings of the European Conference on Computer Vision (ECCV). Munich:Springer, 2018:20-36.
[4] WANG Q T, ZHENG Y, BETKE M. A method for detecting text of arbitrary shapes in natural scenes that improves text spotting[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle:IEEE, 2020:540-541.
[5] LIAO M H, WAN Z Y, YAO C, et al. Real-time scene text detection with differentiable binarization[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York:PKP, 2020:11474-11481.
[6] BAEK Y, LEE B, HAN D, et al. Character region awareness for text detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. California:IEEE, 2019:9365-9374.
[7] WANG W H, XIE E Z, LI X, et al. Pan++:towards efficient and accurate end-to-end spotting of arbitrarily-shaped text[EB/OL]. (2021-05-04)[2021-05-31]. https://ieeexplore.ieee.org/abstract/document/9423611.
[8] LI W, NEULLENS S, BREIER M, et al. Text recognition for information retrieval in images of printed circuit boards[C]//IECON 2014-40th Annual Conference of the IEEE Industrial Electronics Society. Dallas:IEEE, 2014:3487-3493.
[9] ZHANG B Y, ZHAO Y Y, DU Y H, et al. PCB-TD:PCB image dataset[EB/OL]. (2021-05-31)[2021-05-31]. https://mcprl.com/html/dataset/PCBTD.html.
[10] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//3rd International Conference on Learning Representations (ICLR). San Diego:OpenReview, 2015:1-14.
[11] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recog-nition. Las Vegas:IEEE, 2016:770-778.
[12] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.
[13] CAO X K, WANG Z P, ZHAO Y Y, et al. Scale aggregation network for accurate and efficient crowd counting[C]//Proceedings of the European Conference on Computer Vision (ECCV). Munich:Springer, 2018:734-750.
[14] KARATZAS D, GOMEZ-BIGORDA L, NICOLAOU A, et al. ICDAR 2015 competition on robust reading[C]//2015 13th International Conference on Document Analysis and Recognition (ICDAR). Tunis:IEEE, 2015:1156-1160.
[15] SHI B G, YANG M K, WANG X G, et al. Aster:an attentional scene text recognizer with flexible rectification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 41(9):2035-2048.

一种基于深度学习的PCB图像字符检测方法

Character Detection Method for PCB Image Based on Deep Learning

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	刘阳, 滕颖蕾, 牛涛, 郅佳琳. 基于深度强化学习的滤波器剪枝方案[J]. 北京邮电大学学报, 2023, 46(3): 31-36.
[2]	靳梦凡, 黄智濒, 储志强. 复杂环境下多模态指导的点云补全方法[J]. 北京邮电大学学报, 2023, 46(3): 103-108.
[3]	荣震宇刘建毅. 基于Transformer和MLP的眼底血管分割算法[J]. 北京邮电大学学报, 2023, 46(1): 26-31.
[4]	刘金桐, 杨国兴, 刘晓鸿, 王光宇. 针对心电图分类模型的平滑攻击算法[J]. 北京邮电大学学报, 2022, 45(4): 44-50.
[5]	黄柳婷, 刘可欣, 牛凯, 常春, 贺志强. 基于深度学习的哮喘患者CT影像黏液栓自动识别[J]. 北京邮电大学学报, 2022, 45(4): 58-63.
[6]	柳长源, 虎浩媛, 毕晓君. 双线性融合网络的驾驶员分心行为识别[J]. 北京邮电大学学报, 2022, 45(2): 79-84.
[7]	张重生, 陈杰, 纵瑞星, 杨帅磊, 凡高娟. 基于Transformer的低质场景字符检测算法[J]. 北京邮电大学学报, 2022, 45(2): 124-130.
[8]	赵海英, 朱会, 侯小刚. 基于改进EMA单元的传统服饰图像语义分割[J]. 北京邮电大学学报, 2022, 45(1): 69-74.
[9]	贾珺, 冯春燕, 夏海轮, 张天魁, 李成钢. 基于样本均衡与特征交互的通信网络故障预测方法[J]. 北京邮电大学学报, 2021, 44(6): 59-66.
[10]	普运伟, 郭江, 刘涛涛, 吴海潇. 基于多学习单元卷积神经网络的雷达辐射源信号识别[J]. 北京邮电大学学报, 2021, 44(6): 74-82.
[11]	王艺霏, 莫爽, 吴文睿, 范少华, 肖丁. 基于内外卷积网络的网络入侵检测[J]. 北京邮电大学学报, 2021, 44(5): 94-100.
[12]	高慧, 张继威, 来扬, 王文东. 深度学习的人体图像半自动标注系统[J]. 北京邮电大学学报, 2021, 44(1): 104-109.
[13]	蒲悦逸, 王文涵, 朱强, 陈朋朋. 基于CNN-ResNet-LSTM模型的城市短时交通流量预测算法[J]. 北京邮电大学学报, 2020, 43(5): 9-14.
[14]	马向亮, 李冰, 杨丹, 黄克振, 段晓毅. 基于深度学习的类SM4算法S盒逆向分析[J]. 北京邮电大学学报, 2020, 43(5): 118-124.
[15]	张天麒, 康波, 孟祥飞, 刘奕琳, 周颖. 基于U-Net的颅内出血识别算法[J]. 北京邮电大学学报, 2020, 43(3): 92-98.