Abstract
Conventional defect detection and recognition algorithms for integrated circuit (IC) components, used in printed circuit boards (PCBs), are primarily based on automated optical inspection (AOI). These techniques typically extract image features using image processing models, which are heavily dependent on visual cues and can thus be inaccurate. To address these issues, we propose the use of a deep convolutional neural network, an improved LeNet-5 structure called ICChaNet with a deeper structure and more complex parameters. First, the algorithm for character extraction is implemented and used to generate character samples from IC component images. This process includes grayscaling, binarization, and contour extraction, applied to a set of IC component images to establish 53 categories of characters (letters and number with similar symbols removed). Three critical hyperparameters, including learning rate, pooling strategy, and optimization strategy, are then optimized through a comparative analysis. The effect of different network architectures on model efficiency is also investigated by varying the layer depth. A combination classifier strategy is subsequently added to the fully connected layers to strengthen the feature expression in the corresponding classes. Finally, the performance of the proposed ICChaNet model is verified through a comparison with popular CNNs. Experimental results demonstrate that ICChaNet has achieved a classification accuracy of 98.5% and a test average accuracy precision of 97.73%. These results suggest the proposed ICChaNet model is a promising approach for automated character identification.
Similar content being viewed by others
References
Cheong LK, Suandi SA, Rahman S (2019) Defects and components recognition in printed circuit boards using convolutional neural network. Proc ROVISP 547:75–81
Park TH, Kim HJ, Kim N (2006) Path planning of automated optical inspection machines for PCB assembly systems. Int J Control Autom 4(1):96–104
Cho HJ, Park TH (2008) Template matching method for SMD inspection using discrete wavelet transform. Proc SICE 4655216:3198–3201
Crispin AJ, Rankov V (2007) Automated inspection of PCB components using a genetic algorithm template-matching approach. Int J Adv Manuf Technol 35:293–300
Raihan F, Ce W (2017) PCB defect detection using OpenCV with image subtraction method. Proc ICIMTech 8273538:204–209
Anitha DB, Rao M (2017) A survey on defect detection in bare PCB and assembled PCB using image processing techniques. Proc WiSPNET 8299715:39–43
Gang SY, Lim J, Lee JJ (2019) Character recognition of PCB Parts using deep learning. Proc MITA 2019:8–11
Yoon HJ, Su MG, Lee JJ (2019) PCB coating thickness measurement based on laser optical triangulation method. J Inst Control 25(3):212–221
Fabrice N, Gang SY, Lee JJ (2019) Training data sets construction from large data set for PCB character recognition. J Multimed Inf Syst 6(4):225–234
Sun YQ, Wei SD, Chen JZ (2015) SMT product character recognition based on Principal Component analysis. Proc ICEPT 7236579:218–220
Nava CF, Gonzalez FF (2015) OCR for unreadable damaged characters on pcbs using principal component analysis and bayesian discriminant functions. Proc CSCI 165:535–538
Epshtein B, Ofek E, Wexler Y (2010) Detecting text in natural scenes with stroke width transform. Proc CVPR 5540041:2963–2970
Chan WL, Pun CM (2011) Robust character recognition using connected-component extraction. Proc IIHMSP 55:310–313
Jung J, Park T (2006) A PCB character recognition system using rotation-invariant features. J Inst Control 12(3):241–247
Kim W, Lee JJ, Ko Y et al (2018) Parallel pre-process model to improve accuracy of Tesseract-OCR. Proc KISE 2018:641–643
Miskuf M, Zolotov I (2016) Comparison between multi-class classifiers and deep learning with focus on industry 4.0. Proc K&I 7438633:1–5
Dutta S (2018) An overview on the evolution and adoption of deep learning applications used in the industry. Data Min Knowl 8(4):e1257
Yann LC, Yoshua B, Geoffrey H (2015) Deep learning. Nature 521:436–444
Subakti H, Jiang JR (2018) Indoor augmented reality using deep learning for industry 4.0 smart factories. Proc COMPSAC 2:63–68
Sun XH, Gu JN, Tang SX, Li J (2018) Research progress of visual inspection technology of steel products-a review. Appl Sci 8(11):2195
Lacey G, Taylor GW, Areibi S (2016) Deep learning on FPGAs: past, present, future. arXiv:1602.04283:1-9
Lv FY, Wen CL, Bao ZJ et al (2016) Fault diagnosis based on deep learning. Proc ACC 7526751:6851–6856
Wood S, Muthyala R, Jin Y et al (2017) Automated industry classification with deep learning. Proc Big Data 8257920:122–129
Jia XJ, Liu ZH (2021) One-Shot M-Array Pattern Based on Coded Structured Light for Three-Dimensional Object Reconstruction. J Control Sci E ng 2021:6676704
Huang WB, Wei P (2018) A PCB dataset for defects detection and classification. J Latex Class Files 14(8):1–10
Zhang LL, Jin YQ, Yang XS et al (2018) Convolutional neural network-based multi-label classification of PCB defects. J Eng 16:1612–1616
Huang R, Gu JN, Sun XH et al (2019) A Rapid Recognition Method for Electronic Components Based on the Improved YOLO-V3 Network. Electronics 8:825
Qiao K, Zeng L, Chen J et al (2018) Wire segmentation for printed circuit board using deep convolutional neural network and graph cut mode. IET Image Proc 12(5):793–800
Hu B, Wang JH (2020) Detection of PCB Surface Defects with Improved Faster-RCNN and Feature Pyramid Network. IEEE Access 3001349:1–14
Gang SY, Fabrice N, Lee JJ (2020) Coresets for PCB character recognition based on deep learning. Proc ICAIIC 9065271:637–642
Gang SY, Fabrice N, Chung DW et al (2021) Character Recognition of Components Mounted on Printed Circuit Board Using Deep Learning. Sensor 21(9):2921
Lin CH, Wang SH, Lin CJ (2019) Using convolutional neural networks for character verification on integrated circuit components of printed circuit boards. Appl Intell 49(11):4022–4032
Shi BG, Bai X, Yao C (2017) An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans Pattern Anal Mach Intell 39(11):2298–2304
Wei YW, Shen W, Zeng D et al (2018) Multi-oriented text detection from natural scene images based on a CNN and pruning non-adjacent graph edges. Signal Process-Image 64:89–98
Minaee S, Kalchbrenner N, Cambria E et al (2021) Deep Learning Based Text Classification: A Comprehensive Review. ACM Comput Surv 54(62):1–40
Liu ZH, Cheng F, Zhang W (2016) A novel segmentation algorithm for clustered flexional agricultural products based on image analysis. Comput Electron Agr 126:44–54
Jia XJ, Liu ZH (2021) Element extraction and convolutional neural network-based classification for blue calico. Text Res J 91(3–4):261–277
Jia XJ, Deng HT, Teng Z et al (2018) Using contour fitting to extract image elements for blue calico. J Text Res 39(8):150–157
Yann LC, Leon B, Yoshua B et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Liu ZH (2019) Soft-shell shrimp recognition based on an improved AlexNet for quality evaluations. J Food Eng 266:109698
Qiu SS, Gao LP, Wang J (2015) Classification and regression of ELM, LVQ and SVM for e-nose data of strawberry juice. J Food Eng 144:77–85
Angshuman P, Abhinandan G, Rao CA (2018) Calculation of phase fraction in steel microstructure images using random forest classifier. IET Image Proc 12:1370–1377
Alex K, Ilya S, Geoffrey EH (2017) ImageNet classification with deep convolutional neural networks. Commun Acm 60(6):84–90
Liu ZH, Jia XJ, Xu XS (2019) Study of shrimp recognition methods using smart networks. Comput Electron Agr 165:104926
Diederik K, Jimmy B (2015) Adam: a method for stochastic optimization. Proc ICLR 2015:1–15
Acknowledgements
This work was supported in part by the Zhejiang Public Welfare Technology Research Project Fund of China under Grant LGG20F010010, LGG21F030013, and the City Public Welfare Technology Application Research Project of Jiaxing Science and Technology Bureau of China under Grant 2018AY11008 and 2020AY10009. We thank LetPub (www.letpub.com) for its linguistic assistance and scientific consultation during the preparation of this manuscript.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jia, X., Liu, Z. Character Identification for Integrated Circuit Components on Printed Circuit Boards Using Deep Learning. J. Electr. Eng. Technol. 17, 601–616 (2022). https://doi.org/10.1007/s42835-021-00885-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42835-021-00885-4