计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 396-399.doi: 10.11896/jsjkx.210100123

• 图像处理& 多媒体技术 • 上一篇    下一篇

改进穿线法与HOG+SVM结合的数码管图像读数研究

宋一言, 唐东林, 吴续龙, 周立, 秦北轩   

  1. 西南石油大学机电工程学院 成都610500
  • 出版日期:2021-11-10 发布日期:2021-11-12
  • 通讯作者: 唐东林(2727061804@qq.com)
  • 作者简介:920697876@qq.com
  • 基金资助:
    四川省科技支撑计划项目(2017FZ0033)

Study on Digital Tube Image Reading Combining Improved Threading Method with HOG+SVM Method

SONG Yi-yan, TANG Dong-lin, WU Xu-long, ZHOU Li, QIN Bei-xuan   

  1. School of Mechanical and Electrical Engineering,Southwest Petroleum University,Chengdu 610500,China
  • Online:2021-11-10 Published:2021-11-12
  • About author:SONG Yi-yan,born in 1997,M.S.student.His main research interests include image processing,deep learning and target detection.
    TANG Dong-lin,born in 1970,Ph.D,doctoral supervisor.His mian research interests include nondestructive testing and pattern recognition technology.
  • Supported by:
    Sichuan Science and Technology Support Plan Project(2017FZ0033).

摘要: 针对传统投影分割方法在提取单个数码管数字图像时过于依赖图像二值化及图像倾斜校正效果的问题,采用一种基于轮廓提取和轮廓排序相结合的数码管图像分割方法,实验证明该方法相比投影分割法在对数字区域的分割成功率上提高了13.5%;针对传统穿线法对数码管数字1识别度较低和机器学习算法运行用时较长的问题,提出一种基于六段数码管特征的改进穿线法与HOG+SVM方法相结合的数码管数字识别方法,该方法对数码管数字的识别准确率比传统穿线法提高了约4.5%,且平均运行时间仅为HOG+SVM方法的1/5。实验结果证明了这种方法在进行数码管读数时的可靠性和优越性。

关键词: HOG+SVM, 穿线法, 轮廓分割, 识别和读数, 数码管, 图像处理

Abstract: In traditional projection method when rely too much on a single digital image are extracted image binarization and tilt correction effect problem,using a method based on contour extraction and contour sort of digital image segmentation method,experimental results show this method is compared with the projection segmentation on the success rate for segmenting the digital area increased by 13.5%;Against traditional threading method for number 1 low recognition and machine learning algorithms run takes longer problem,put forward an improved,based on the six characteristics of segment digital tube threading method and the HOG+SVM method with the combination of digital identification method,the method of digital tube digital identification accuracy than traditional threading method by about 4.5%,and the average elapsed time only 1/5 ofthe HOG+SVM method.The experimental results show the reliability and effectiveness of the method in digital tube reading.

Key words: Contour segmentation, Digital tube, HOG+SVM, Identifying and reading, Image processing, Stringing method

中图分类号: 

  • TP751
[1]CHEN G,HUZ Z F,ZHEN C.Fast recognition algorithm ofdigital instrument based on feature detection[J].The Chinese test,2019,45(4):150-154.
[2]CHEN Y.Research on the development and application dynamics of machine vision technology[J].Wireless Interconnection Technology.2018,15(19):147-148.
[3]CHEN X.Research on Automatic Detection System of Power Instrument Based on Machine Vision[D].Harbin:Harbin Institute of Technology,2015.
[4]DENG Q N,SHI X L.Indoor digital display instrument reading recognition of substation[J].Industrial Instrumentation and Automation,2018(2):86-89.
[5]HE W,XU G,RONG Z,et al.Automatic Calibration System for Digital-Display Vibrometers Based on Machine Vision[J].Metrology & Measurement Systems,2014,21(2):317-328.
[6]LIU Z,LUO Z,GONG P,et al.The research of character recognition alg-orithm for the automatic verification of digital instrument[C]//International Conference on Measurement,Information and Control.IEEE,2014:177-181.
[7]CHEN Z X.A digital display digital recognition al-gorithm[J].Computer Knowledge and Technology,2014,10(23):5496-5500.
[8]DING S,REN G Y,ZHANG F M.Improved threading method for caliper image recognition[J].Journal of Measurement,2019,40(5):765-769.
[9]DU B.Research on Instrumentation Positioning and Identifica-tion Method in Patrol Inspection System[D].Wuhan:Huazhong University of Science and Technology,2018.
[10]LIN J P,LIAO Y P.Automatic recognition of digital instrument reading based on OpenCV and LSSVM[J].Microcomputers and Applications,2017,36(2):37-40.
[11]LIU J.Research on Automatic Character Recognition of Digital Instrument Based on Image Processing[J].Information Technology,2020,341(4):84-88.
[12]CHEN J L.Detection method of concrete based on image processing method[J].Chinese Journal of Liquid Crystals and Displays,2020,35(4):395-401.
[13]CHEN Z B,ZHANG C,SONG Y.Application of GrayscaleStretch Retinex in Large-scale Smoke Image Enhancement[J].Infrared and Laser Engineering,20141 43(9):3146-3150.
[14]IEEE Xplore Abstract- A Threshold Selection Method fromGray-Level His-tograms[J].IEEE Transactions on Systems Man & Cybernetics,1979.
[15]DALAL N,TRIGGS B.Histograms of oriented gradients forhuman detec-tion[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR 2005).IEEE,2005,1:886-893.
[16]WANG L.Research on Vehicle Detection Algorithm Based on HOG and SVM[D].Wuhan:Huazhong University of Science and Technology,2017.
[1] 郭拯危, 付泽文, 李宁, 白澜.
高分辨率斜视聚束SAR回波仿真加速算法研究
Study on Acceleration Algorithm for Raw Data Simulation of High Resolution Squint Spotlight SAR
计算机科学, 2022, 49(8): 178-183. https://doi.org/10.11896/jsjkx.210600066
[2] 刘伟业, 鲁慧民, 李玉鹏, 马宁.
指静脉识别技术研究综述
Survey on Finger Vein Recognition Research
计算机科学, 2022, 49(6A): 1-11. https://doi.org/10.11896/jsjkx.210400056
[3] 来腾飞, 周海洋, 余飞鸿.
视频流的实时景深延拓算法
Real-time Extend Depth of Field Algorithm for Video Processing
计算机科学, 2022, 49(6A): 314-318. https://doi.org/10.11896/jsjkx.201100187
[4] 詹瑞, 雷印杰, 陈训敏, 叶书函.
基于多重差异特征网络的街景变化检测
Street Scene Change Detection Based on Multiple Difference Features Network
计算机科学, 2021, 48(2): 142-147. https://doi.org/10.11896/jsjkx.200500158
[5] 张育龙, 王强, 陈明康, 孙静涛.
图像去雨算法在云物联网应用中的研究综述
Survey of Intelligent Rain Removal Algorithms for Cloud-IoT Systems
计算机科学, 2021, 48(12): 231-242. https://doi.org/10.11896/jsjkx.201000055
[6] 冯一凡, 赵雪青, 师昕, 杨坤.
基于光照叠加的颜色恒常计算方法
Light Superposition-based Color Constancy Computational Method
计算机科学, 2021, 48(11A): 386-390. https://doi.org/10.11896/jsjkx.210200053
[7] 谢海平, 李高源, 杨海涛, 赵洪利.
超分辨率重构遥感图像分类研究
Classification Research of Remote Sensing Image Based on Super Resolution Reconstruction
计算机科学, 2021, 48(11A): 424-428. https://doi.org/10.11896/jsjkx.210300132
[8] 姚楠, 张征.
基于三维图像的疤痕面积计算
Scar Area Calculation Based on 3D Image
计算机科学, 2021, 48(11A): 308-313. https://doi.org/10.11896/jsjkx.201100044
[9] 宋娅菲, 谌雨章, 沈君凤, 曾张帆.
基于改进残差网络的水下图像重建方法
Underwater Image Reconstruction Based on Improved Residual Network
计算机科学, 2020, 47(6A): 500-504. https://doi.org/10.11896/JsJkx.200100084
[10] 蔡玉鑫, 汤志伟, 赵博, 杨明, 吴禹非.
基于嵌入式多核DSP的加速软件系统
Accelerated Software System Based on Embedded Multicore DSP
计算机科学, 2020, 47(6A): 622-625. https://doi.org/10.11896/JsJkx.190400079
[11] 马虹.
基于5G的视觉辅助BDS移动机器人融合定位算法
Fusion Localization Algorithm of Visual Aided BDS Mobile Robot Based on 5G
计算机科学, 2020, 47(6A): 631-633. https://doi.org/10.11896/JsJkx.190400156
[12] 苗益, 赵增顺, 杨雨露, 徐宁, 杨皓然, 孙骞.
图像描述技术综述
Survey of Image Captioning Methods
计算机科学, 2020, 47(12): 149-160. https://doi.org/10.11896/jsjkx.200500039
[13] 凌晨, 张鑫彤, 马雷.
基于Mask R-CNN算法的遥感图像处理技术及其应用
Remote Sensing Image Processing Technology and Its Application Based on Mask R-CNN Algorithms
计算机科学, 2020, 47(10): 151-160. https://doi.org/10.11896/jsjkx.190900119
[14] 郭兰英, 韩睿之, 程鑫.
基于可变形卷积神经网络的数字仪表识别方法
Digital Instrument Identification Method Based on Deformable Convolutional Neural Network
计算机科学, 2020, 47(10): 187-193. https://doi.org/10.11896/jsjkx.191000035
[15] 朱德利, 杨德刚, 胡蓉, 万辉.
适于移动终端字符识别环境的自适应多阈值二值化方法
Adaptive Multi-level Threshold Binaryzation Method for Optical Character Recognition in Mobile Environment
计算机科学, 2019, 46(8): 315-320. https://doi.org/10.11896/j.issn.1002-137X.2019.08.052
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!