Generating Virtual Samples Based on Prior Knowledge in Pointer Meter Recognition

被引：0
|
作者：
Ma B. [1 ,2 ,3 ]
Cai W. [1 ]
Zheng F. [1 ]
机构：
[1] College of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing
[2] Beijing Key Laboratory of Healthy Monitoring Control and Fault Self-Recovery for High-end Machinery, Beijing University of Chemical Technology, Beijing
[3] Key Laboratory of Engine Health Monitoring and Networking, Beijing University of Chemical Technology, Ministry of Education, Beijing
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2019年 / 31卷 / 09期
关键词：
Convolutional neural networks; Pointer meter; Prior knowledge; Small sample; Virtual sample generation;
D O I：
10.3724/SP.J.1089.2019.17612
中图分类号：
学科分类号：
摘要：
In order to solve the problems that the existing method of pointer meter recognition depended on the validity of preprocessing and the lack of generalization ability, a hybrid method of automatic recognition on pointer meters combining deep convolutional neural networks with virtual samples is proposed. The deep convolutional neural networks are used to adaptively extract the key features of the instrument image to avoid the interference of irrelevant information. The prior knowledge is used to construct the virtual sample generation model of the pointer meter to solve the small sample problem faced by the deep convolutional neural networks. Simulation data, experimental data and practical application were applied to validate the method. The results show that the method achieves better effect and good robustness with its application on different instruments under various scenes. © 2019, Beijing China Science Journal Publishing Co. Ltd. All right reserved.
引用
收藏
页码：1549 / 1557
页数：8
相关论文
共 20 条
  • [1] Xu L., Shi W., Fang T., Pointer meter reading recognition system used in patrol robot, Chinese Journal of Scientific Instrument, 38, 7, pp. 1782-1790, (2017)
  • [2] Zhang W., Xiong Q., Zhang J., Et al., Pointer type meter reading recognition based on visual saliency, Journal of Computer-Aided Design & Computer Graphics, 27, 12, pp. 2282-2295, (2015)
  • [3] Song W., Zhang W., Zhang J., Et al., Meter reading recognition method via the pointer region feature, Chinese Journal of Scientific Instrument, 35, pp. 50-58, (2014)
  • [4] Zhang J., Shi R., Chen S., Auto-reading method for precision pointer meter based on ICM, Chinese Journal of Scientific Instrument, 37, 12, pp. 2866-2872, (2016)
  • [5] Mo W., Pei L., Huang Q., Et al., Development of automatic verification system for high precision pointer instrument based on template matching and table searching, Electrical Measurement & Instrumentatio, 54, 12, pp. 100-105, (2017)
  • [6] Yang Z.J., Niu W.N., Peng X.J., Et al., An image-based intelligent system for pointer instrument reading, Proceedings of the 4th IEEE International Conference on Information Science and Technology, pp. 780-783, (2014)
  • [7] Zheng C., Wang S.R., Zhang Y.H., Et al., A robust and automatic recognition system of analog instruments in power system by using computer vision, Measurement, 92, pp. 413-420, (2016)
  • [8] Huang Y., Wang R., Yue L., Research progress of machine vision instrument recognition, Process Automation Instrumentation, 30, 8, pp. 58-60, (2009)
  • [9] Jin J.Q., Fu K., Zhang C.S., Traffic sign recognition with hinge loss trained convolutional neural networks, IEEE Transactions on Intelligent Transportation Systems, 15, 5, pp. 1991-2000, (2014)
  • [10] Guan S., Zhang Q., Xie H., Et al., Convolutional neural network model of CT images recognition, Journal of Computer-Aided Design & Computer Graphics, 30, 8, pp. 1530-1535, (2018)
12