Abstract
The existence of glass defects seriously affects the quality of glass products. Traditional glass defect recognition methods based on convolutional neural networks (CNNs) suffer from a long training time and low recognition accuracy. By introducing convolutional auto-encoder (CAE) into a CNN, we propose an auto-encoding convolutional neural network, and pre-train the convolution kernel by CAE, thereby reducing the training time caused by randomly initializing the convolution kernel. At the same time, in order to cope with the over-fitting problem caused by a small sample of glass defect dataset, we employ a fuzzy support vector machine (FSVM) instead of the Softmax classifier to classify glass defects. Furthermore, we propose a multi-channel auto-encoding convolutional neural network model to deal with misidentification of inclusions and tumor type defects due to small differences in feature space. The model takes a defect image and its enhanced image as input, and averages the output of each channel as the final output, thus achieving accurate recognition of glass defects. Experimental results show that the glass defect recognition method based on auto-encoding convolutional neural network can greatly reduce the training time while maintaining the same classification accuracy rate. The glass defect recognition method based on multi-channel auto-encoding convolutional neural network achieves a recognition rate of 95% for both inclusion and tumor type defects. As a result, and the overall recognition rate is increased from 92.6% using a single channel to 97%.
Similar content being viewed by others
References
Wenhui, H., Ye, W., Yi, J., Changan, Z.: Deep features based on a DCNN model for classifying imbalanced weld flaw types. Measurement 131, 482–489 (2019)
Li, D., Liang, L.Q., Zhang, W.J.: Defect inspection and extraction of the mobile phone cover glass based on the principal components analysis. Int. J. Adv. Manuf. Technol. 73, 1605–1614 (2014)
Liu, T.Y., Bao, J.S., Wang, J.L., Zhang, Y.M.: A hybrid CNN–LSTM algorithm for online defect recognition of CO2 welding. Sensors 18, 4369 (2018)
Yang, K., Sun, Z.Y., Wang, A.H., Liu, R.Z., Sun, Q.L., Wang, Y.: Deep hashing network for material defect image classification. IET Comput. Vision 12, 1112 (2018)
Gaoyang, L., Xiaohua, W., Xi, L., Aijun, Y., Mingzhe, R.: Partial discharge recognition with a multi-resolution convolutional neural network. Sensors 18, 3512 (2018)
Park, J.K., Kwon, B.K., Park, J.H.: Machine learning-based imaging system for surface defect inspection. Int. J. Precis. Eng. Manuf. Green Technol. 3, 303–310 (2016)
Soukup, D., Huber-Mark, R.: Convolutional neural networks for steel surface defect detection from photometric stereo images. Adv. Vis. Comput. 8887, 668–677 (2014)
Masci, J., Meier, U., Ciresan, D.: Steel defect classification with Max-Pooling Convolutional Neural Networks. In: International Joint Conference on Neural Networks. pp. 1–6 (2012)
Haselmann, M., Gruber, D.: Supervised machine learning based surface inspection by synthetizing artificial defects. In: IEEE International Conference on Machine Learning & Applications. pp. 390–395 (2018)
Yong, J., Jialiang, W., Zhaoba, W.: Conjugate gradient neural network-based online recognition of glass defects. Concurr. Comput. Pract. Exp. 29, e3768 (2017)
He, L., Zheng, S.X., Chen, W.: OptQuant: distributed training of neural networks with optimized quantization mechanisms. Neurocomputing 340, 233–244 (2019)
Chen, J.G., Li, K.L., Bilal, K.: A bi-layered parallel training architecture for large-scale convolutional neural networks. IEEE Trans. Parallel Distrib. Syst. 30(5), 965–976 (2019)
Wu, X., Wang, Y.X., Tang, H.J.: A structure-time parallel implementation of spike-based deep learning. Neural Netw. 113, 72–78 (2019)
Liu, M.L., Grana, D.: Accelerating geostatistical seismic inversion using TensorFlow: a heterogeneous distributed deep learning framework. Comput. Geosci. 124, 37–45 (2019)
Ayinde, B.O., Zurada, J.M.: Deep learning of constrained autoencoders for enhanced understanding of data. In: IEEE Transactions on Neural Networks and Learning Systems, pp. 1–11 (2017)
Sun, Y., Xue, B., Zhang, M.: A particle swarm optimization-based flexible convolutional auto-encoder for image classification. IEEE Trans. Neural Netw. Learn. Syst. (2017). https://doi.org/10.1109/TNNLS.2018.2881143
Dendi, S.V.R., Dev, C., Kothari, N.: Generating image distortion maps using convolutional autoencoders with application to no reference image quality assessment. IEEE Signal Process. Lett. 26, 89–93 (2018)
Deng, Y.H., Sander, A., Faulstich, L., Denecke, K.: Autoencoders for learning template spectrograms in electrocorticographic signals. Artif. Intell. Med. 16, 16–25 (2019)
Lin, C.F., Wang, S.D.: Fuzzy support vector machines. IEEE Trans. Neural Netw. 13, 464–471 (2002)
Chiang, J.H., Hao, P.Y.: A new kenel based fuzzy clustering approach support vector clustering With cell Growing. IEEE Trans. Fuzzy Syst. 11, 518–527 (2003)
Lin, Y., Lee, Y., Wahba, G.: Support vector machines for classification in nonstandard situations. Mach. Learn. 46, 191–202 (2001)
Jeevakala, S., Therese, A.B.: Sharpening enhancement technique for MR images to enhance the segmentation. Biomed. Signal Process. Control 41, 21–30 (2018)
Ravisankar, P., Sharmila, T.S., Rajendran, V.: Acoustic image enhancement using Gaussian and laplacian pyramid—a multiresolution based technique. Multimedia Tools Appl. 77, 5547–5561 (2017)
Subramani, B., Veluchamy, M.: MRI brain image enhancement using brightness preserving adaptive fuzzy histogram equalization. Int. J. Imaging Syst. Technol. 28, 217–222 (2019)
Paul, A., Bhattacharya, P., Maity, S.P., Bhattacharyya, B.K.: Plateau limit-based tri-histogram equalisation for image enhancement. IET Image Process. 12, 1617–1625 (2019)
Savic, M.S., Peric, Z.H., Simic, N.: Coding algorithm for grayscale images based on Linear Prediction and dual mode quantization. Expert Syst. Appl. 42, 7285–7291 (2015)
Jimenez-Fernandez, V.M., Vazquez-Leal, H., Filobello-Nino, U.A.: Exploring the use of two-dimensional piecewise-linear functions as an alternative model for representing and processing grayscale-images. J. Appl. Res. Technol. 14, 311–318 (2016)
Kamandar, M.: Automatic color image contrast enhancement using Gaussian mixture modeling, piecewise linear transformation, and monotone piecewise cubic interpolant. SIViP 12, 625–632 (2017)
Acknowledgements
The research project is supported by Shanxi Scholarship Council of China (No. 2016-084), Shanxi Province Science and Technology Tackling Key Project (No. 201603D121006-1), and Shanxi Province Foundation (General Program No. 201801D121150).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jin, Y., Zhang, D., Li, M. et al. A Fuzzy Support Vector Machine-Enhanced Convolutional Neural Network for Recognition of Glass Defects. Int. J. Fuzzy Syst. 21, 1870–1881 (2019). https://doi.org/10.1007/s40815-019-00697-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40815-019-00697-9