Industrial Optical Character Recognition System in Printing Quality Control of Hot-Rolled Coils Identification
- 12 Downloads
This work presents a system designed to detect printing errors and misidentifications on steel coils that could lead to tracking problems and even guide to the delivery of the wrong product to the final client. An optical character recognition system is proposed to extract the printed identification of steel coils from images captured by a fixed camera in an industrial environment. The method considers different digital image processing techniques to deal with the significant lighting and printing variation observed, followed by a segmentation process that extracts and aligns the characters originally printed in an arch form, ending with a classification routine based on a convolutional neural network. The proposed system presents an approach to treat lighting variations in images, covering low contrast, darker and brighter images. Experiment carried out on a data set with approximately 20,000 images achieved an accuracy higher than 98%, supporting the validity of the proposed method.
KeywordsOptical character recognition Intelligent manufacturing Digital image processing Convolutional neural networks
The authors thank ArcelorMittal Tubarão for supporting and making available the images used in this work. Patrick Marques Ciarelli thanks the partial funding of his research work provided by CNPq (Grant 312032/2015-3).
- Achieving 90% accuracy in Object Recognition Task on CIFAR-10 Dataset with Keras: Convolutional Neural Networks. URL: https://appliedmachinelearning.blog/2018/03/24/achieving-90-accuracy-in-object-recognition-task-on-cifar-10-dataset-with-keras-convolutional-neural-networks/. Accessed 04 May 2019.
- El Harraj, A., & Raissouni, N. (2015). Ocr accuracy improvement on document images through a novel pre-processing approach. Signal & Image Processing : An International Journal (SIPIJ), 6(4), 1–18.Google Scholar
- Five powerful CNN architectures. URL: https://medium.com/datadriveninvestor/five-powerful-cnn-architectures-b939c9ddd57b. Accessed 04 May 2019.
- Gonzalez, Rafael C., & Woods, Richard E. (2007). Digital image processing (3rd ed.). London: Pearson.Google Scholar
- Islam, N., Islam, Z., & Noor, N. (2016). A survey on optical character recognition system. Journal of Information & Communication Technology (JICT), 10(2), 1–4.Google Scholar
- Liu, H., Gao, W., Miao, J., Zhao, D., Deng, G., & Li, J. (2001). Illumination compensation and feedback of illumination feature in face detection. In Proceedings of IEEE International Conferences on Info-tech and Info-net, vol. 23, pp. 444–449.Google Scholar
- MEPS—world carbon steel prices–\$US/metric ton. URL: http://www.meps.co.uk/World. Accessed 04 May 2019.
- Mudhsh, M. A., & Almodfer, R. (2017). Arabic handwritten alphanumeric character recognition using very deep neural network. Information, 8, 1–14.Google Scholar
- OpenCV2: Template Matching Documentation. URL: https://docs.opencv.org/3.0-beta/doc/py_tutorials/py_imgproc/py_template_matching/py_template_matching.html. Accessed 04 May 2019.
- Pal, K. K., & Sudeep K. S. (2016). Preprocessing for image classification by convolutional neural networks. In IEEE international conference on recent trends in electronics, information & communication technology (RTEICT), pp. 1778–1781.Google Scholar
- Smith R. (2007). An overview of the Tesseract OCR engine. In Ninth international conference on document analysis and recognition, 2007. ICDAR 2007., (vol. 2, pp. 629–633). IEEE.Google Scholar
- Wang, Xiuying, Yu, Shengping, Zheng, Binglin, & Chai, Tianyou (2006). Intelligent scheduling system of steelmaking and continuous casting based on ERP/MES/PCS. In The sixth world congress on intelligent control and automation, 2006. WCICA 2006, (vol. 2, pp. 7381–7384). IEEE.Google Scholar
- Wick, C., Reul, C., & Puppe, F. (2018). Calamari—a high-performance tensorflow-based deep learning package for optical character recognition. Computing research repository (CoRR)—arXiv, pp. 1–12.Google Scholar
- Yim, J., & Sohn K.-A. (2017). Enhancing the performance of convolutional neural networkson quality degraded datasets. Computing research repository (CoRR)—arXiv, pp. 1–8.Google Scholar