Abstract
Aiming at the problem of low recognition accuracy of digital display meter readings when the inspection robot performs inspection tasks, a YOLOv5-based digital display meter detection and recognition algorithm for distribution cabinets is proposed. For the digital display meter image captured by the inspection robot spherical camera, the YOLOv5 model is used to locate the target character area. After scale normalization, image correction, filtering and noise removal and other image pre-processing operations, the character recognition is completed in combination with the traditional machine vision algorithm, and the reading results are automatically output. For the characteristics of digital tube characters, the threading method, support vector machine algorithm and PaddleOCR algorithm are used for comparison, and a suitable algorithm model is selected to recognize numeric, alphabetic and decimal point characters. The experimental results show that the accuracy of detecting and identifying digital display meters using the YOLOv5 model and PaddleOCR algorithm is 95.3%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gao, J., Ye, H.: An effective algorithm for secondary recognition of digital images of water meters. J. Southeast Univ. (Nat. Sci. Ed.) 43(S1), 153–157 (2016)
Zhang, Y.L.: Research on instrument dial parameter symbol recognition technology. Guangdong University of Technology (2008)
Liu, W.L.: Research and implementation of digital recognition in seven-segment digital display instrumentation. Dalian University of Technology (2013)
Hua, Z.X., Shi, H.B., Luo, Y., et al.: Identification of digital instrumentation detection in substations based on lightweight YOLO-v4 model. J. Southwest Jiaotong Univ., 1–11 (2021)
Xiong, X., Chen, X.D., Wu, L., Lin, X.L.: Digital dial reading recognition based on convolutional memory neural network. Comb. Mach. Tools Autom. Mach. Technol. 07, 72–75 (2019)
Zhang, L.Y.: Research on detection and identification algorithm of substation instrumentation based on deep learning. Tianjin University of Technology (2021)
Tang, P., Liu, Y., Wei, H.G., Dong, X.Y., et al.: Automatic identification algorithm of digital meter readings based on mask-RCNN offshore booster station. Infrared Laser Eng. 50(S2), 163–170 (2021)
Qu, C.R., Chen, L.W., Wang, J.S., Wang, S.G.: Research on industrial digital meter recognition algorithm based on deep learning. Appl. Sci. Technol., 1–7 (2022)
Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real-time object detection. In: Computer Vision & Pattern Recognition (2016)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: IEEE Conference on Computer Vision & Pattern Recognition, pp. 6517–6525 (2017)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)
Yun, S., Han, D., Oh, S.J., et al.: CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6023–6032 (2019)
Lin, T.Y., Dollár, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Liu, S., Qi, L., Qin, H., et al.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759–8768 (2018)
Rezatofighi, H., Tsoi, N., Gwak, J.Y., et al.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 658–666 (2019)
Zheng, Z., Wang, P., Liu, W., et al.: Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12993–13000 (2020)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)
Fang, X.W., Fu, X.W.: ID card segmentation algorithm based on projection method and Caffe framework. Comput. Eng. Appl. 53(23), 113–117 (2017)
Qiu, D., Weng, M., Yang, H.-T.: A fast lane line detection method based on improved probabilistic Hough transform. Comput. Technol. Dev. 30(5), 43–48 (2020)
Song, Y.Y., Tang, D.L., Wu, X.L., et al.: Study on digital tube image reading by combining improved threading method and HOG+ SVM method. Comput. Sci. 48(S2), 396–399+440 (2021)
Wang, X.D., Wei, C.B., Feng, H.R., et al.: Digital identification method for digital display instruments in substation protection rooms based on SVM. Electron. Meas. Technol. 42(2), 92–95 (2019)
Chen, X., Xu, S.Y., et al.: Identification of braided river reservoir inclusions based on support vector machine and principal component analysis. J. China Univ. Petr. (Nat. Sci. Edn) 45(04), 22–31 (2021)
Liao, M., Wan, Z., Yao, C., et al.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 11474–11481 (2020)
Yu, D., Li, X., Zhang, C., et al.: Towards accurate scene text recognition with semantic reasoning networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12113–12122 (2020)
Li, W., Cao, L., Zhao, D., et al.: CRNN: Integrating classification rules into neural network. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 IEEE (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhou, Y., Zhang, Y., Wang, C., Sun, S., Wang, J. (2022). Detection and Identification of Digital Display Meter of Distribution Cabinet Based on YOLOv5 Algorithm. In: Zhang, H., et al. Neural Computing for Advanced Applications. NCAA 2022. Communications in Computer and Information Science, vol 1637. Springer, Singapore. https://doi.org/10.1007/978-981-19-6142-7_23
Download citation
DOI: https://doi.org/10.1007/978-981-19-6142-7_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-6141-0
Online ISBN: 978-981-19-6142-7
eBook Packages: Computer ScienceComputer Science (R0)