Abstract
We propose a new method based on a machine learning technique to detect the mixed-characters on the surface of all kinds of cables applied in industry. Firstly, the images of these characters are captured by a high precision CCD, and then, the captured images need to be preprocessed, normalized, and divided into multiple images. Each image includes a single character. Finally, the training set image is sorted and optimized. We establish a convolutional neural network for the characters recognition, and its parameters are improved based on character features. The average recognition rate of mixed-character is 92.6%. Experimental results show a recognition rate based on machine learning could be higher than the one by using other algorithms.
This is a preview of subscription content, log in via an institution to check access.
References
Davies, E.R.: Machine Vision: Theory, Algorithms, Practicalities, pp. 1–16. Elsevier (2004)
Steger, C., Ulrich, M., Wiedemann, C.: Machine vision algorithms and application. Illumination 5(2.1), 1 (2008)
Zhou, W.J.: Research and Application of Online Idle Speed Detection and Precise Control Problem Based on Machine Vision. Shanghai University, Shanghai (2014). (In Chinese)
Wang, Y., Xia, R.Z., Chen, H.L.: Milling machine vision inspection system design. J. Test Technol. 29(3), 235–240 (2015). (In Chinese)
Wu, H.H., Zhang, X.M.: Pre-blow detection algorithm for multi-pin type placement devices. J. Electron. Meas. Technol. 25(11), 998–1005 (2011). (In Chinese)
Xu, Y.S., Gu, J.H., Tao, Z.: Handwritten character recognition based on improved BP neural network. Commun. Technol. 44(5), 106–109 (2011). (In Chinese)
Steger, C., Urich, M., Wiedemann, C.: Machine Vision Algorithms and Applications, Bilingual edn. In: Yang, S.S., Wu, D.J., Duan, D.S. (trans.). Tsinghua University Press, Beijing (2011)
Zhang, W., Wang, Y.P., Xue, G.X.: Digital Image Processing and Machine Vision. People’s Posts and Telecommunications Press, Beijing (2012). (In Chinese)
Wu, H.H., Zeng, X.R., Lai, Y.J., Wu, F.P.: Machine vision based harness connector character detection. Test Technol. 32(2), 174–179 (2018). (In Chinese)
Li, Y.J.: Handwritten English Letter Recognition Based on LVQ Neural Network. Guangdong University of Technology, Guangdong (2008). (In Chinese)
Gao, L.: Handwritten English Letter Recognition Based on BP Neural Network. North University, Shanxi (2009). (In Chinese)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Han, L., Zou, S., He, D., Zhou, W.J. (2020). Detection for Mixed-Characters Based on Machine Learning. In: Jain, V., Patnaik, S., Popențiu Vlădicescu, F., Sethi, I. (eds) Recent Trends in Intelligent Computing, Communication and Devices. Advances in Intelligent Systems and Computing, vol 1006. Springer, Singapore. https://doi.org/10.1007/978-981-13-9406-5_21
Download citation
DOI: https://doi.org/10.1007/978-981-13-9406-5_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9405-8
Online ISBN: 978-981-13-9406-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)