| Title |
Deep Learning?based Number Detection and Recognition for Gas Meter Reading |
| Authors |
Seung Hyun Lee;Tae Young Han;Min Kyu Lee;Kang Il Lee;Byung Cheol Song |
| DOI |
https://doi.org/10.5573/IEIESPC.2019.8.5.367 |
| Keywords |
Gas meter?reading system; Computer vision; Image processing; Convolutional neural network |
| Abstract |
The meter reading?system field has been researched from conventional methods centered on image processing technology to techniques based on learning methods such as machine learning or deep learning. The biggest problem for meter reading systems based on computer vision is difficulty in recognizing the various kinds of meters. In fact, there are more than five major manufacturers for the meters installed in Korea. There are different meter reading areas, ID regions, and number formats by version. Because of these problems, most of the meter reading is still done hands-on. In this paper, we present an automatic meter?reading system that can work simply and efficiently, compared to existing meter reading systems that need a skilled worker. Our meter reading system consists of three parts: i) detection of meter-reading and ID regions using You Only Look Once (YOLO), ii) digit segmentation for recognition, and iii) convolutional neural network (CNN)-based digit recognition. It is possible to robustly detect and recognize various meter types by using the method presented here. Therefore, it can provide an environment where gas meter checkers can work efficiently without inconvenient procedures. |