Research on Mining Platform Scale License Plate Based on Deep Learning

4th International Conference on Energy Equipment Science and Engineering

Guo, Xiucai^1 ; Xu, Dan^1 ; Zhang, Shasha^1

Xi'an University of Science and Technology, Yanta Middle Road 58, Xi'an, Shaanxi Province, China^1

关键词: Accuracy problems;    Automatic identification;    Character segmentation;    License plate detection;    License plate location;    License plate recognition;    Vehicle automations;    Weighing instruments;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/242/2/022048/pdf
DOI  :  10.1088/1755-1315/242/2/022048

来源: IOP

【 摘 要 】

Weighbridge is a mechanically operated large weighing instrument widely used in the coal industry. In order to effectively improve the vehicle automation management level of coal mines and accelerate the circulation of coal in coal mines, this paper studies the automatic identification technology of mining platform scale license plates. This paper studies the traditional license plate recognition process, namely: license plate detection, license plate location, character segmentation and character recognition. The shortcomings of the traditional license plate recognition process are analyzed. It is found that the traditional license plate recognition process has many processes, and the connection between each algorithm module is not tight enough. The accuracy problems existing in each step are accumulated, which will eventually cause serious loss of speed and accuracy. In this regard, this paper proposes an endto-end license plate recognition method, using the deep learning AlexNet model for end-to-end license plate recognition training, overcoming the problems caused by the traditional license plate recognition process for license plate recognition.