Abstract
Surface defects significantly deteriorate piezoresistor quality. We propose an accurate end-to-end classification method for piezoresistor surface defects based on an incremental branch growth convolutional neural network (IBG-CNN) for automatic CNN construction. First, an incremental branch (IB) is proposed to grow a CNN dynamically. Then, IBG-CNN establishes and trains a starting network based on IB, which is then grown continuously using the IBG algorithm. The next generation of the growing network is trained using the pretrained previous generation, which significantly accelerates the search process of the network model. A CNN based on IBG-CNN for classifying six piezoresistor defect types was automatically built on one GPU in only approximately 16 h. A test dataset of 6248 images was evaluated using the mean average precision (mAP). The experimental results demonstrate that the classification accuracy of our algorithm (mAP = 0.935) is higher than or very close to those of state-of-the-art methods, i.e., conventional CNN-based methods and the efficient neural architecture search (ENAS).
Similar content being viewed by others
References
Abadi M, Barham P, Chen J et al. (2016) TensorFlow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX symposium on operating systems design and implementation (OSDI ‘16), USENIX Association. 265–283
Arshaghi A, Ashourian M, Ghabeli L (2020) Feature selection based on buzzard optimization algorithm for potato surface defects detection. Multimed Tools Appl 79:26623–26641. https://doi.org/10.1007/s11042-020-09236-3
Carrera D, Manganini F, Boracchi G, Lanzarone E (2017) Defect detection in SEM images of nanofibrous materials. IEEE Trans Ind Inform 13:551–561. https://doi.org/10.1109/TII.2016.2641472
Chondronasios A, Popov I, Jordanov I (2016) Feature selection for surface defect classification of extruded aluminum profiles. Int J Adv Manuf Technol 83:33–41. https://doi.org/10.1007/s00170-015-7514-3
Elsken T, Metzen JH, Hutter F (2018) Neural architecture search: a survey. J Mach Learn Res 20:1–21. https://doi.org/10.1007/978-3-030-05318-5_11
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of IEEE conference on computer vision and pattern recognition. IEEE Computer Society, Seattle, WA, pp 580–587
Glorot X, Bordes A, Bengio Y (2010) Deep sparse rectifier neural networks. J Mach Learn Res 15:315–323
Gong B, Xiao L, Li C, Yang T (2019) Research on target location method based on varistor image. In: Greivenkamp J, Tanida J, Jiang Y, Gong H, Lu J, Liu D (eds) 8th applied optics and photonics China. SPIE, Beijing, China, p 7
He Z, Sun L (2015) Surface defect detection method for glass substrate using improved Otsu segmentation. Appl Opt 54:9823–9830. https://doi.org/10.1364/AO.54.009823
Iandola FN, Moskewicz MW, Ashraf K, Han S, Dally WJ, Keutzer K (2017) SqueezeNet: Alexnet-level accuracy with 50x fewer parameters and <1MB model size. arXiv preprint arXiv:1602.07360
Jia Y, Shelhamer E, Donahue J, Karayev S, Long J (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia. Association for Computing Machinery, pp 675–678
Kang G, Gao S, Yu L, Zhang D (2019) Deep architecture for high-speed railway insulator surface defect detection: Denoising autoencoder with multitask learning. IEEE Trans Instrum Meas 68:2679–2690. https://doi.org/10.1109/TIM.2018.2868490
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1106–1114
Kwon BK, Won JS, Kang DJ (2015) Fast defect detection for various types of surfaces using random forest with VOV features. Int J Precis Eng Manuf 16:965–970. https://doi.org/10.1007/s12541-015-0125-y
Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539
Li X, Liao R, Zhou J, Leung P, Yan M, Ma H (2017) Classification of morphologically similar algae and cyanobacteria using Mueller matrix imaging and convolutional neural networks. Appl Opt 56:6520–6530. https://doi.org/10.1364/AO.56.006520
Lin M, Chen Q, Yan S (2014) Network in network. arXiv preprint arXiv:1312.4400
Park JK, Kwon BK, Park JH, Kang DJ (2016) Machine learning-based imaging system for surface defect inspection. Int J Precis Eng Manuf Green Technol 3:303–310. https://doi.org/10.1007/s40684-016-0039-x
Park Y, Kweon IS (2016) Ambiguous surface defect image classification of AMOLED displays in smartphones. IEEE Trans Ind Inform 12:597–607. https://doi.org/10.1109/TII.2016.2522191
Pham H, Guan MY, Zoph B, Le QV, Dean J (2018) Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268
Roy D, Panda P, Roy K (2018) Tree-CNN: a hierarchical deep convolutional neural network for incremental learning. Neural Netw 121:148–160. https://doi.org/10.1016/j.neunet.2019.09.010
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Szegedy C, Liu W, Jia Y, Sermanet P (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition. IEEE, Boston, MA, pp 1–9
Takahashi R, Matsubara T, Uehara K (2020) Data augmentation using random image cropping and patching for deep CNNs. IEEE Trans Circuits Syst Video Technol 30:2917–2931. https://doi.org/10.1109/TCSVT.2019.2935128
Tan A, Zhou G, He M (2020) Surface defect identification of citrus based on KF-2D-Renyi and ABC-SVM. Multimed Tools Appl 80:9109–9136. https://doi.org/10.1007/s11042-020-10036-y
Tsai DM, Wu SC, Chiu WY, Carrera D, Manganini F, Boracchi G, Lanzarone E (2013) Defect detection in solar modules using ICA basis images. IEEE Trans Ind Inform 9:122–131. https://doi.org/10.1109/TII.2012.2209663
Wang HF, Cao J, Zhao XM, Wang XM, Wang GP (2017) Detection of HF-ERW status by neural network on imaging. Int J Precis Eng Manuf 18:931–936. https://doi.org/10.1007/s12541-017-0110-8
Wu S, Wu YB, Cao D, Zheng C (2019) A fast button surface defect detection method based on Siamese network with imbalanced samples. Multimed Tools Appl 78:34627–34648. https://doi.org/10.1007/s11042-019-08042-w
Xi J, Shentu L, Hu J, Li M (2017) Automated surface inspection for steel products using computer vision approach. Appl Opt 56:184–192. https://doi.org/10.1364/AO.56.000184
Xiao T, Zhang J, Yang K, Peng Y, Zhang Z (2014) Error-driven incremental learning in deep convolutional neural network for large-scale image classification. In: Proceedings of the 22nd ACM international conference on multimedia. ACM, Orlando, FL, pp 177–186
Yi L, Li G, Jiang M (2017) An end-to-end steel strip surface defects recognition system based on convolutional neural networks. Steel Res Int 88:1600068. https://doi.org/10.1002/srin.201600068
Zhong Z, Yan J, Wu W, Shao J, Liu CL (2018) Practical block-wise neural network architecture generation. In: IEEE/CVF conference on computer vision and pattern recognition. IEEE, Piscataway, NJ, pp 2423–2432
Zoph B, Le Q (2017) Neural architecture search with reinforcement learning. In: 5th international conference on learning representations, OpenReview.net, Toulon, France, pp 1,2,5,7,8.
Acknowledgments
We would like to thank NVIDIA for providing the Titan X GPU used in this study.
Funding
This study was partially supported by the National Natural Science Foundation of China (62166012, 61941202) and the Guangxi Natural Science Foundation (2018GXNSFBA281081).
Author information
Authors and Affiliations
Contributions
Methodology, L.H. and T.-J.Y.; writing (original draft preparation), L.H.; supervision, Y.-G.Z.; funding acquisition, L.H.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflicts 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
Huang, L., Zhao, YG. & Yang, TJ. Piezoresistor defect classification using convolutional neural networks based on incremental branch growth. Multimed Tools Appl 81, 16743–16760 (2022). https://doi.org/10.1007/s11042-022-12651-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12651-3