Object Detection Model Training Technique for Numeric Text Detection in Analog Power Meter Images
AUTHORS
Young Hwa Cha,Department of Computer Science, Kwangwoon University, Seoul, Korea
Byung Joon Park,Department of Computer Science, Kwangwoon University, Seoul, Korea
ABSTRACT
Recently, with the expansion of the demand response market, the need to automatically read power meters is increasing. In addition, computer vision using deep neural networks has rapidly developed, and object detection, the task of finding a specific object in an image, has now reached high accuracy. There are several studies on the subject of automatic power meter reading. However, studies that apply object detection to reading meters are difficult to find. Automatic power meter reading is generally divided into the task of finding the number corresponding to the usage and the task of recognizing the number. In this paper, we only deal with finding numbers using object detection. Training is needed to create an object detection model that finds only the numeric area in the meter. The important factors in training a model are the amount of training data and the number of training epochs. Training a lot of epochs with a lot of training data will show high detection performance, but it takes a lot of time to prepare for training and training data. In this paper, we present the amount of training data and the number of epochs that can take the least time to train an object detection model with a detection performance of over 99%. Also, the results of various experiments performed to find this parameter are recorded in the paper.
KEYWORDS
Object detection, Computer vision, Machine learning, Deep neural networks, Automatic power meter reading
REFERENCES
[1] P. Palensky and D. Dietrich, “Demand side management: demand response, intelligent energy systems, and smart loads,” IEEE Transactions on Industrial Informatics, vol.7, no.3, pp.381-388, (2011)
[2] L. A. Elrefaei, A. Bajaber, S. Natheir, N. AbuSanab, and M. Bazi, “Automatic electricity meter reading based on image processing,” IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies, pp.1-5, (2015)
[3] A. Anis, M. Khaliluzzaman, M. Yakub, N. Chakraborty, and K. Deb, “Digital electric meter reading recognition based on horizontal and vertical binary pattern,” 2017 3rd International Conference on Electrical Information and Communication Technology (EICT), Khulna, pp.1-6, (2017)
[4] J. Sun, Yuzhong Ma, Han Yang, Ning Wang, Yu Ding, Aiping Song, Yongwei Zhu, and Juntong Xi, “Character recognition method for low-contrast images of numerical instruments,” 2018 IEEE 3rd International Conference on Image, Vision and Computing, Chongqing, China, pp.157-162, (2018)
[5] Li Liu, Wanli Ouyang, Xiaogang Wang, Paul Fieguth, Jie Chen, Xinwang Liu, and Matti Pietikäinen, “Deep learning for generic object detection: a survey,” International Journal of Computer Vision, vol.128, pp.261-318, (2020)
[6] Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi, “You only look once: unified, real-time object detection,” The IEEE Conference on Computer Vision and Pattern Recognition, pp.779-788, (2016)
[7] R. Girshick, “Faster R-CNN,” The IEEE International Conference on Computer Vision, pp.1440-1448, (2015)
[8] https://www.tensorflow.org/
[9] http://host.robots.ox.ac.uk/pascal/VOC/