Abstract
In order to detect the defects of smart meter liquid crystal display (LCD) screen quickly and accurately, this paper proposes a method based on line segment detector (LSD) and deep learning. Characters of smart meter LCD screen can be divided into two types: ordinary characters and digital tube characters. Convolutional neural network (CNN) is used to locate and identify the ordinary characters. Since there may be certain missing segment in digital tube characters, conventional text detection methods are not applicable, and template matching method is used for detecting them. Compared with the whole screen, the digital tube area is very small, and the relative positions of the digital tube characters of smart meter of most manufacturers are nearly the same, so the detection rate of the template matching method is extremely high and the method can be commonly used. The whole detection process is as follows: First, horizontal straight lines got by LSD are used for tilt correction. Secondly, CNN is used to locate and identify an ordinary character of the meter screen to determine whether it is missing or not. Then, whether there are missing segments in the digital tube area is determined by template matching method. At last, the experimental results show that the accuracy of the method for detecting the character defects of LCD screen is about 96%, and the accuracy of the electric quantity identification function of the method is about 97%.
Similar content being viewed by others
References
Al Mahmud N (2020) Performance Analysis of Different Acoustic Features based on LSTM for Bangla Speech Recognition[J]. Int J Multimedia Applic 12(4):17–25
Cha YJ, You K, Choi W (2016) Vision-based detection of loosened bolts using the Hough transform and support vector machines. Autom Constr 71:181–188
Chen L, Li S (2018) Improvement Research and Application of Text Recognition Algorithm Based on CRNN[C]. SPML '18 Proceedings of the 2018 International Conference on Signal Processing and Machine Learning
Chunlei R (2013) Research of the energy meter detection system based on machine vision [D].Zhejiang University of Technology
Gioi RGV, Jakubowicz J, Morel JM et al (2010) LSD: a fast line segment detector with a false detection control[J]. IEEE Trans Pattern Analys Mach Intell 32(4):722–732
Graves A, Fernández S, Gomez F (2006) Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks[C]. Proceedings of the 23rd international conference on Machine learning. 369–376
Guiping D, Li D, Yue G (2015) The exterior type consistency inspection system for smart meter[J]. Lect Notes Electr Eng, 197–203
He B, Xiyang O, Xingzhe H (2014) Quality detecting method of electricity meter LCD screen based on image processing[J]. Electr Meas Instrum 51(9):25–28
Hongyi J, Liping Z, Zhangpeng O (2017) Text recognition of natural scene image based on MSER and Tesseract[J]. Comp Knowl Technol, 213–216
Kiranyaz S, Zabihi M, Rad AB, Ince T, Hamila R, Gabbouj M (2020) Real-time phonocardiogram anomaly detection by adaptive 1D convolutional neural networks[J]. Neurocomputing 411:291–301
Lai W-x, Wang W, Huang B-b, Ren H, Shi T-l (2009) Fast Template Matching Based on Local Entropy Difference[C]. 2009 2nd International Congress on Image and Signal Processing, 1–5
Min Y, Xiao B, Dang J, Yue B, Cheng T (2018) Real time detection system for rail surface defects based on machine vision. EURASIP J Image Video Process 3:1–11
Na Y, Zhiyuan Q, Zhongtao L, Sha Z (2014) Rapid Algorithm of Normalized Cross-Correlation Matching[J]. J Inf Eng Univ 15(02):215–218
Neogi N, Mohanta DK, Dutta PK et al (2014) Eur J Image Video Process 50:1–19
Sahani SK, Adhikari G, Das BK (2011) A fast template matching algorithm for aerial object tracking[C]. 2011 International Conference on Image Information Processing, 1–6
Sharma H, Jalal AS (2020) Incorporating external knowledge for image captioning using CNN and LSTM[J]. Mod Phys Lett B 34(28):12
Sheng W (2019) Design and implementation of quality inspection system for smart meter display defects[D]. University of Electronic Science and Technology of China
Shengcheng W (2018) The machine vision inspection system of electric energy meter LCD screen based on LSD [D]. Zhengzhou University
Shi B, Bai X, Yao C (2016) An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition[J]. IEEE Trans Pattern Anal Mach Intell 39(11):2298–2304
Song R, Cai Q, Wang Z, Su H, Shao X, Li W, Jin P (2018) A novel quality test method of electricity meter LCD Screen based on image processing[J]. J Phys Conf Ser
Tong W (2020) Research on Intelligent Detection Method of Traffic Signs Using Convolutional Neural Network[D].Beijing University of Architecture and Architecture
Weichen L, Duming T (2011) Defect inspection in low-contrast LCD images using hough transform-based nonstationary line detection[J]. IEEE Trans Ind Inform 7(1):136–147
Wojna Z, Gorban AN, Lee DS et al. (2017) Attention-Based Extraction of Structured Information from Street View Imagery[J]. arXiv, 844–850
Xie G, Lin M, Yanhui DAI (2015) Research on LCD screen appearance detection of smart meter in low-contrast[J]. Comput Eng Appl 50(2):247–251
Yang SW, Lin CS, Lin SK, Chiang HT (2014) Automatic defect recognition of TFT array process using gray level co-occurrence matrix[J]. Opt-Int J Light Electron Opt 125:2671–2676
Yang Y, Xie R, Jia W, Chen Z, Yang Y, Xie L, Jiang BX (2021) Accurate and automatic tooth image segmentation model with deep convolutional neural networks and level set method[J]. Neurocomputing 419:108–125
Yongqing C, Zhu X, Wang Y, Guo J, Lianqing C (2014) Research on image recognition of internal thread. Tool Eng 12:77–79
Yu P (2019) A method of detecting defects of electric meter LCD screen based on LSD and CNN [D]. Zhengzhou University
Zhi T, Weilin H, Tong H, Pan H, Yu Q (2016) Detecting text in natural image with connectionist text proposal network[J]. Comput Vis – ECCV 2016, 9912,56–72
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Pei, B., Peng, Y. & Luo, Y. A method of detecting defects of smart meter LCD screen based on LSD and deep learning. Multimed Tools Appl 80, 35955–35972 (2021). https://doi.org/10.1007/s11042-020-10481-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-10481-9