Recognition of plate identification numbers using convolution neural network and character distribution rules

被引：0
作者：
Wang H. [1 ]
Wei S. [1 ]
Huang R. [1 ]
Deng S. [2 ]
Yuan F. [2 ]
Xu A. [2 ]
Zhou J. [3 ]
机构：
[1] School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing
[2] School of Metallurgical and Ecological Engineering, University of Science and Technology Beijing, Beijing
[3] China Shipbuilding NDRI Engineering Co.Ltd, Shanghai
来源：
ISIJ International | 2019年 / 59卷 / 11期
基金：
中国国家自然科学基金;
关键词：
Characters distribution rules; Convolution neural network; Data augmentation; Non-Maximum Suppression; Plate identification numbers;
D O I：
10.2355/isijinternational.ISIJINT-2019-128
中图分类号：
学科分类号：
摘要：
Recognition of plate identification numbers (PINs) is of much importance for the automation of the iron and steel production. The recognition of PINs in industrial site is a challenging problem due to complicated background, low quality of characters. Conventional image processing algorithms are employed to extract the numbers, but it is difficult for these methods to locate and recognize the numbers on the plates in complex industrial production by manually designed features. The end-to-end convolution neural network is employed to solve these problems by automatically extracted features. These features seldom combine the real production rules. A delicate recognition method of PINs using convolution neural network and characters distribution rules is proposed. The PINs are roughly recognized by convolution neural network with Non-Maximum Suppression (NMS), and the PINs are exactly processed using the character distribution rules. Experiment results demonstrate that the method proposed can arrive at a very high recognition rate 96.32% and improve the recognition rate by 54.07% compared with the end-to-end convolution neural network. © 2019 ISIJ
引用
收藏
页码：2044 / 2051
页数：7
相关论文
共 32 条
[11]  
Jaderberg M., Vedaldi A., Zisserman A., Proc. European Conf. On Computer Vision, (2014)
[12]  
Wang T., Wu D.J., Coates A., Proc. Int. Conf. On Pattern Recognition, (2012)
[13]  
Wang Y., Mao H., Yi Z., Knowl. Based Syst., 118, (2017)
[14]  
Qawaqneh Z., Mallouh A.A., Barkana B.D., Knowl. Based Syst., 115, (2017)
[15]  
LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D., Neural Comput, 1, (1989)
[16]  
Nair V., Hinton G.E., Proc. Int. Conf. On Machine Learning, (2010)
[17]  
Krizhevsky A., Sutskever I., Hinton G.E., Proc. Advances in Neural Information Processing Systems, (2012)
[18]  
Szegedy C., Toshev A., Erhan D., Proc. Advances in Neural Information Processing Systems, (2013)
[19]  
Jaderberg M., Simonyan K., Vedaldi A., Zisserman A., Int. J. Comput. Vis., 116, (2016)
[20]  
Liao M., Shi B., Bai X., Wang X., Liu W., 31st AAAI Conf. On Artificial Intelligence, (2017)
1234