A Deep Learning-Based Surface Defect Inspection System for Smartphone Glass
In recent years, convolutional neural network has become a solution to many image processing problems due to high performance. It is particularly useful for applications in automated optical inspection systems related to industrial applications. This paper proposes a system that combines the defect information, which is meta data, with the defect image by modeling. Our model for classification consists of a separate model for embedding location information in order to utilize the defective locations classified as defective candidates and ensemble with the model for classification to enhance the overall system performance. The proposed system incorporates class activation map for preprocessing and augmentation for image acquisition and classification through optical system, and feedback of classification performance by constructing a system for defect detection. Experiment with real-world dataset shows that the proposed system achieved 97.4% accuracy and through various other experiments, we verified that our system is applicable.
KeywordsDeep learning Convolutional neural network Class activation map Smartphone glass inspection Defect detection Augmentation Image preprocessing
This research was supported by Samsung Electronics Co., Ltd.
- 1.Sun, J., Wang, P., Luo, Y.K., Li, W.: Surface defects detection based on adaptive multiscale image collection and convolutional neural networks. IEEE Trans. Instrum. Measur. 1–11 (2019)Google Scholar
- 2.Natarajan, V., Hung, T.Y., Vaikundam, S., Chia, L.T.: Convolutional networks for voting-based anomaly classification in metal surface inspection. In: IEEE International Conference on Industrial Technology, pp. 986–991 (2017)Google Scholar
- 7.Gupta, E., Kushwah, R.S.: Combination of global and local features using DWT with SVM for CBIR. In: International Conference on Reliability, Infocom Technologies and Optimization, pp. 1–6 (2015)Google Scholar
- 8.Zhou, B., Khosla, A., Lapedriza, A., Olivia, A., Torralba, A.: Learning deep features for discriminative localization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)Google Scholar
- 10.Dong, X., Taylor, C.J., Cootes, T.F.: Small defect detection using convolutional neural network features and random forests. In: European Conference on Computer Vision, pp. 1–15 (2018)Google Scholar
- 12.Yang, H., Chen, Y., Song, K., Yin, Z.: Multiscale feature-clustering-based fully convolutional autoencoder for fast accurate visual inspection of texture surface defects. IEEE Trans. Autom. Sci. Eng. 99, 1–18 (2019)Google Scholar
- 14.Sainath, T., Parada, C.: Convolutional neural networks for small-footprint keyword spotting. In: InterSpeech, pp. 1478–1482 (2015)Google Scholar
- 15.Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625–2634 (2015)Google Scholar
- 16.Rippel, O., Snoek, J., Adams, R.P.: Spectral representations for convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 2449–2457 (2015)Google Scholar
- 17.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar