[1]蒋子敏,刘宁钟,沈家全.基于轻量级网络的 PCB 芯片文字识别[J].计算机技术与发展,2021,31(12):55-60.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 010]
　JIANG Zi-min,LIU Ning-zhong,SHEN Jia-quan.PCB Chip Text Recognition Based on Lightweight Network[J].,2021,31(12):55-60.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 010]
点击复制

基于轻量级网络的 PCB 芯片文字识别()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年12期
页码:
55-60
栏目:
图形与图像
出版日期:
2021-12-10

文章信息/Info

Title:
PCB Chip Text Recognition Based on Lightweight Network
文章编号:
1673-629X(2021)12-0055-06
作者:
蒋子敏; 刘宁钟; 沈家全
南京航空航天大学 计算机科学与技术学院,江苏 南京 211106
Author(s):
JIANG Zi-min; LIU Ning-zhong; SHEN Jia-quan
School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
关键词:
PCB 芯片; 文字识别; 轻量级神经网络; 卷积神经网络; 循环神经网络
Keywords:
PCB chip; text recognition; lightweight neural network; convolutional neural network; recurrent neural network
分类号:
TP391.4
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 12. 010
摘要:
随着人工智能的兴起,深度学习技术在多个领域有了广泛的应用与发展,将深度学习技术与 PCB 芯片文字识别相结合,实现具体的场景应用,具有重要意义。 基于深度学习进行文字识别,完成图像中文字信息的自动获取,进一步提高了准确率,极大地节约了人工及时间成本。 但传统深度学习模型巨大的参数量以及内存消耗等限制了其在小型设备如移动终端上的应用与发展,难以满足人们日益增长的需求。 基于此, 该文提出了一种基于轻量级网络的文字识别算法LWTR。 该算法框架主要包括卷积神经网络( 进行特征提取) 、循环神经网络( 进行标签预测) 以及 CTC( 实现转录) ,最终得到预测序列。 为减小模型参数量,进行通道数的统一并采用多路小卷积及堆叠 Dense Layer 充分提取特征。 同时,为加速网络的收敛,提高模型的泛化能力,引入 BN 归一化。 结果表明,该算法在 PCB 芯片数据集中文字识别准确率达到了89. 58% ,与现有文字识别算法相比,在准确率几乎没有下降的情况下具有更小的模型与更快的速度。
Abstract:
With the rise of artificial intelligence,deep learning technology has been widely used and developed in many fields. It is of great significance to combine deep learning technology with PCB chip text recognition and realize specific domain applications. Finishing text recognition based on deep learning to realize automatic acquisition of text information in images has further improved recognition accuracy and greatly saved labor? and time costs. However,the huge parameter amount and memory consumption of the traditional deep learning models limit its application and development on small devices such as mobile terminals,and it is difficult to meet the increasing needs of people nowadays. Therefore, a text recognition algorithm LWTR is proposed based on lightweight network. The algorithm framework mainly includes convolutional neural network for feature extraction,recurrent neural network for label prediction and CTC to achieve transcription,and finally gets the predicted sequence. In order to reduce the amount of model parameters, unified number of channels,multi-path small convolution and stacked Dense Layer are used to fully extract features. At the same time,in order to accelerate the convergence of the network and improve the generalization ability of the model,Batch Normalization ( BN) is introduced. The results show that the proposed algorithm has achieved 89. 58% of the text recognition accuracy in our PCB chip dataset. And compared with the existing text recognition algorithms,it has a smaller model and faster speed with almost no decrease in accuracy.

相似文献/References:

[1]陈梓洋,王宇飞,钱侃,等. 自然场景下基于区域检测的文字识别算法[J].计算机技术与发展,2015,25(07):230.
　CHEN Zi-yang,WANG Yu-fei,QIAN Kan,et al. Character Recognition Algorithm Based on Region Detection in Natural Scene[J].,2015,25(12):230.
[2]任荣梓,高航. 基于反馈合并的中英文混排版面OCR技术研究[J].计算机技术与发展,2017,27(03):39.
　REN Rong-zi,GAO Hang. Investigation on Layout Analysis Technology of Chinese and English Mixed OCR Based on Feedback Merging[J].,2017,27(12):39.
[3]张婷婷,马明栋,王得玉.OCR 文字识别技术的研究[J].计算机技术与发展,2020,30(04):85.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 016]
　ZHANG Ting-ting,MA Ming-dong,WANG De-yu.Research on OCR Technology[J].,2020,30(12):85.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 016]
[4]章 安,马明栋.基于 Tesseract 文字识别的预处理研究[J].计算机技术与发展,2021,31(01):73.[doi:10. 3969 / j. issn. 1673-629X. 2021. 01. 013]
　ZHANG An,MA Ming-dong.Research on Preprocessing Based on Tesseract Text Recognition[J].,2021,31(12):73.[doi:10. 3969 / j. issn. 1673-629X. 2021. 01. 013]
[5]曾 悦,马明栋.基于 Tesseract_OCR 文字识别的研究[J].计算机技术与发展,2021,31(11):76.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 013]
　ZENG Yue,MA Ming-dong.Research on Text Recognition Based on Tesseract_OCR[J].,2021,31(12):76.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 013]
[6]童 攀,龙炳鑫,拥 措 *.基于注意力机制藏文乌金体古籍文字识别研究[J].计算机技术与发展,2023,33(10):163.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 025]
　TONG Pan,LONG Bing-xin,YONG Cuo*.Research on Tibetan Ujin Ancient Book Character Recognition Based on Attention Mechanism[J].,2023,33(12):163.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 025]
[7]岳霄,景诗云,史伟.基于改进DenseNet的西夏文识别研究[J].计算机技术与发展,2024,34(10):46.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0181]
　YUE Xiao,JING Shi-yun,SHI Wei.Study on Recognition of Xixia Text Based on Improved DenseNet[J].,2024,34(12):46.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0181]
[8]李子含,屈乐达,刘思源.基于FM-MobileViT网络的拓片甲骨文字识别[J].计算机技术与发展,2025,(05):23.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0020]
　LI Zi-han,QU Le-da,LIU Si-yuan.Rubbing Oracle Bone Character Recognition Based on FM-MobileViT[J].,2025,(12):23.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0020]

更新日期/Last Update: 2021-12-10