Abstract
Convolutional neural networks (CNNs) play an important role in an increasing number of image processing tasks. There is an obvious demand to improve their classification performance and efficiency. Current research in this area tends to focus on developing increasingly complex models and algorithms to achieve this end. However, research into computer vision techniques and data augmentation tends to be neglected. This paper demonstrates that even a very simple CNN model achieves high performance in surface defect classification on the NEU dataset thanks to image preprocessing and data augmentation. The initial F1-score of 0.9646 without image preprocessing increases to 0.9727 when preprocessing is carried out. The simple CNN then achieves an F1-score of 0.9854 after data augmentation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chazhoor, A., Ho, E., Gao, B., Woo, W.: A review and benchmark on state-of-the-art steel defects detection. SN Comput. Sci. 5, 114 (2024)
Cumbajin, E., et al.: A systematic review on deep learning with CNNs applied to surface defect detection. J. Imaging 9(10), 193 (2023)
Cumbajin, E., et al.: A real-time automated defect detection system for ceramic pieces manufacturing process based on computer vision with deep learning. Sensors 24(1), 232 (2024)
Garrido-Hidalgo, C., Roda-Sanchez, L., Fernández-Caballero, A., Olivares, T., Ramírez, F.J.: Internet-of-Things framework for scalable end-of-life condition monitoring in remanufacturing. Integr. Comput. Aided Eng. 31(1), 1–17 (2024)
Gómez-Sirvent, J.L., de la Rosa, F.L., Sánchez-Reolid, R., Morales, R., Fernández-Caballero, A.: Defect classification on semiconductor wafers using Fisher vector and visual vocabularies coding. Measurement 202, 111872 (2022)
Górriz, J.M., et al.: Computational approaches to explainable artificial intelligence: advances in theory, applications and trends. Inf. Fus. 100, 101945 (2023)
He, X., Chang, Z., Zhang, L., Xu, H., Chen, H., Luo, Z.: A survey of defect detection applications based on generative adversarial networks. IEEE Access 10, 113493–113512 (2022)
Huang, S.H., Pan, Y.C.: Automated visual inspection in the semiconductor industry: a survey. Comput. Ind. 66, 1–10 (2015)
Iannino, V., et al.: A hybrid approach for improving the flexibility of production scheduling in flat steel industry. Integr. Comput. Aided Eng. 29(4), 367–387 (2022)
Jha, S.B., Babiceanu, R.F.: Deep CNN-based visual defect detection: survey of current literature. Comput. Ind. 148, 103911 (2023)
Lin, J., Ma, L., Yao, Y.: A spectrum-domain instance segmentation model for casting defects. Integr. Comput. Aided Eng. 29(1), 63–82 (2022)
de la Rosa, F.L., Gómez-Sirvent, J.L., Morales, R., Sánchez-Reolid, R., Fernández-Caballero, A.: A deep residual neural network for semiconductor defect classification in imbalanced scanning electron microscope datasets. Appl. Soft Comput. 131, 109743 (2022)
de la Rosa, F.L., Gómez-Sirvent, J.L., Morales, R., Sánchez-Reolid, R., Fernández-Caballero, A.: Defect detection and classification on semiconductor wafers using two-stage geometric transformation-based data augmentation and SqueezeNet lightweight convolutional neural network. Comput. Ind. Eng. 183, 109549 (2023)
de la Rosa, F.L., Gómez-Sirvent, J.L., Sánchez-Reolid, R., Morales, R., Fernández-Caballero, A.: Geometric transformation-based data augmentation on defect classification of segmented images of semiconductor materials using a ResNet50 convolutional neural network. Exp. Syst. Appl. 206, 117731 (2022)
de la Rosa, F.L., Sánchez-Reolid, R., Gómez-Sirvent, J.L., Morales, R., Fernández-Caballero, A.: A review on machine and deep learning for semiconductor defect classification in scanning electron microscope images. Appl. Sci. 11(20), 9508 (2021)
Pang, W., Tan, Z.: A steel surface defect detection model based on graph neural networks. Meas. Sci. Technol. 35(4), 046201 (2024)
Pizer, S.M., et al.: Adaptive histogram equalization and its variations. Comput. Vis. Graph. Image Process. 39(3), 355–368 (1987)
Roda-Sanchez, L., Olivares, T., Garrido-Hidalgo, C., de la Vara, J.L., Fernández-Caballero, A.: Human-robot interaction in Industry 4.0 based on an Internet of Things real-time gesture control system. Integr. Comput. Aided Eng. 28(2), 159–175 (2021)
Schmedemann, O., Baass, M., Schoepflin, D., Schüppstuhl, T.: Procedural synthetic training data generation for AI-based defect detection in industrial surface inspection. Procedia CIRP 107, 1101–1106 (2022)
Zhang, Y., Shen, S., Xu, S.: Strip steel surface defect detection based on lightweight YOLOv5. Front. Neurorobotics 17, 1263739 (2023). https://doi.org/10.3389/fnbot.2023.1263739
Acknowledgements
Grant 2023-PRED-21291 funded by Universidad de Castilla-La Mancha and by “ESF Investing in your future”. Grant BES-2021-097834 funded by MCIN/AEI/ 10.13039/501100011033 and by “ESF Investing in your future”. Grant 2022-GRIN-34436 funded by Universidad de Castilla-La Mancha and by “ERDF A way of making Europe”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
de la Rosa, F.L., Moreno-Salvador, L., Gómez-Sirvent, J.L., Morales, R., Sánchez-Reolid, R., Fernández-Caballero, A. (2024). Improved Surface Defect Classification from a Simple Convolutional Neural Network by Image Preprocessing and Data Augmentation. In: Ferrández Vicente, J.M., Val Calvo, M., Adeli, H. (eds) Bioinspired Systems for Translational Applications: From Robotics to Social Engineering. IWINAC 2024. Lecture Notes in Computer Science, vol 14675. Springer, Cham. https://doi.org/10.1007/978-3-031-61137-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-61137-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-61136-0
Online ISBN: 978-3-031-61137-7
eBook Packages: Computer ScienceComputer Science (R0)