Abstract
With the development of remote automatic recording of utility meter readings, the problems of locating an analog display instrument against a complex background and recognition instruments with inconsistent scales are highlighted. This paper presents an automatic recognition method based on deep learning using the Faster-RCNN algorithm, which can locate the instrument position quickly and accurately in images with large amounts of noisy interference. By using the LeNet-5 convolutional neural network and the proportional relation between the pointer position and both ends of the scale, the number on the dial is recognized automatically. Experimental results showed that the Faster-RCNN algorithm can effectively detect the instrument position in images with large amounts of interference, thus laying an important foundation for subsequent pointer processing and reading recognition. Furthermore, the combination of number recognition and pointer location can make this method effective for different types of instruments with different ranges, which achieves better recognition than traditional approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Data Availability Statement
The original images [.jpg] data used to support the findings of this study are available from the corresponding author upon request.
References
Sablatnig, R., Kropatsch, W.G.: Automatic reading of analog display instruments. In: Proceedings of the 12th IAPR International Conference on Pattern Recognition, Computer Vision and Image Processing, 1994, vol. 1, pp. 794–797. IEEE (1994)
Sablatnig, R., Kropatsch, W.G.: Application constraints in the design of an automatic reading device for analog display instruments. In: Proceedings of the Second IEEE Workshop on Applications of Computer Vision 1994, pp. 205–212. IEEE(1994)
Basca, C.A., Talos, M., Brad, R.: Randomized hough transform for ellipse detection with result clustering. In: The International Conference on IEEE Computer as a Tool, 2005, EUROCON 2005, vol. 2, pp. 1397–1400 (2005)
Prasad, D.K., Leung, M.K.H., Cho, S.Y.: Edge curvature and convexity based ellipse detection method. Pattern Recogn. 45(9), 3204–3221 (2012)
Wang, Q., Fang, Y., Wang, W., et al.: Research on automatic reading recognition of index instruments based on computer vision. In: International Conference on Computer Science and Network Technology, pp. 10–13. IEEE (2014)
Han, J., Li, E., Tao, B., et al.: Reading recognition method of analog measuring instruments based on improved hough transform. In: International Conference on Electronic Measurement and Instruments, pp. 337–340. IEEE (2011)
Shen, X., Cao, M., Lu, Y., et al.: Research on automatic indication values of pointer gauges based on computer vision. In: 2016 China International Conference on Electricity Distribution (CICED), pp. 1–5. IEEE (2016)
Corra Alegria, E., Cruz Serra, A.: Automatic calibration of analog and digital measuring instruments using computer vision. IEEE Trans. Instrum. Measur. 49(1), 94–99 (2000)
Xu, L., Fang, T., Gao, X.: An automatic recognition method of pointer instrument based on improved Hough Transform. In: International Society for Optics and Photonics, Applied Optics and Photonics China (AOPC2015), 96752T–96752T-10 (2015)
Ning, Z.: Automatic recognition method for instrument display based on BP neural network. Control Autom. 158, 198 (2006)
Zhu, H.X.D.O.C.: Pointer instrument recognition based on BP network and improved Hough transform. Electr. Meas. Instrum. 05 (2015)
Lee, C., Kim, H.J., Oh, K.W.: Comparison of faster R-CNN models for object detection. In: 2016 16th International Conference on Control, Automation and Systems (ICCAS), pp. 107–110. IEEE (2016)
Jiang, H., Learned-Miller, E.: Face detection with the faster R-CNN. In: 2017 12th IEEE International Conference on Automatic Face Gesture Recognition (FG 2017), pp. 650–657. IEEE (2017)
Girshick, R., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Computer Vision and Pattern Recognition, pp. 580–587. IEEE (2014)
Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision IEEE Computer Society, pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
Acknowledgment
The authors thank the financial support for this work from Chinese National Natural Science Foundation (61672248, 61370105).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
The authors declare that there is no conflict of interest regarding the publication of this paper.
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, Z., Liu, K., Qiang, X. (2020). Recognition of an Analog Display Instrument Based on Deep Learning. In: Pan, L., Liang, J., Qu, B. (eds) Bio-inspired Computing: Theories and Applications. BIC-TA 2019. Communications in Computer and Information Science, vol 1160. Springer, Singapore. https://doi.org/10.1007/978-981-15-3415-7_44
Download citation
DOI: https://doi.org/10.1007/978-981-15-3415-7_44
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3414-0
Online ISBN: 978-981-15-3415-7
eBook Packages: Computer ScienceComputer Science (R0)