Image Binarization Method of Equal-thickness Butt Welds Based on Regional Optimization

Abstract

Abstract: Due to the reflected surfaces of the grooves，complicated appearances of multi-layer and multi-pass welding grooves，and splatters，the images had the problems of excessive gray levels，uneven distribution of the gray level，and random noises.The image binarization method of equal-thickness butt welds was proposed based on regional optimization.An adaptive method for ROI definition was established to shrink the original images.Based on the distribution characteristics of neighborhood gray difference，an algorithm was proposed to divide the ROI images into two regions-flatness and intensity.With high-quality binary images as the target，the optimal model for the judgment of laser stripe regions was established to determine the regions with the optimal results.Binary processing was completed by using the gray mean values of the regions and was taken as threshold.The experimental results have good evaluation from subjectivity and objectivity.The method is satisfied the real-time requirements of various thickness plates and multi-layer and multi-pass welding.

Key words: equal-thickness butt weld, binarization method;region of interest(ROI), regional determination, optimization model

摘要： 坡口镜面反射、多层多道焊坡口形貌复杂和飞溅等现象，使图像存在灰度级多、灰度分布不均和随机噪声等问题，为此提出了一种基于区域优化的等厚对接焊缝图像二值化方法。提出自适应定义ROI算法以缩减图像；基于邻域灰度极差值的分布，将ROI图像分为平缓和剧烈两区域；进一步以高质量二值化图像为目标，建立了区域判定优化模型，由最优结果确定焊缝光带区域，将该区域灰度均值作为阈值，完成二值化处理。实验结果的主观和客观评价较优，满足多层多道焊和多厚度规格钢板的实时性焊接要求。

关键词: 等厚对接焊缝, 二值化方法, 感兴趣区域, 区域判定, 优化模型

CLC Number:

WANG Xingdong1;YANG Yalun1;KONG Jianyi1;SHI Yi2. Image Binarization Method of Equal-thickness Butt Welds Based on Regional Optimization[J]. China Mechanical Engineering.

王兴东1;杨雅伦1;孔建益1;施毅2. 基于区域优化的等厚对接焊缝图像二值化方法[J]. 中国机械工程.

References

[1]YOU D，GAO X，KATAYAMA S.WPD-PCA-based Laser Welding Process Monitoring and Defects Diagnosis by Using FNN and SVM[J].IEEE Transactions on Industrial Electronics，2015，62(1):628-636.
[2]VILLAN A F，ACEVEDO R G，ALVAREZ E A，et al.Low-cost System for Weld Tracking Based on Artificial Vision[J].IEEE Transactions on Industry Applications，2011，47(3):1159-1167.
[3]GAO X，YOU D，KATAYAMA S.Infrared Image Recognition for Seam Tracking Monitoring during Fiber Laser Welding[J].Mechatronics，2012，22(4):370-380.
[4]乐健，张华，叶艳辉,等.基于旋转电弧传感机器人立焊焊缝的跟踪[J].上海交通大学学报，2015，49(3):348-352.
LE Jian，ZHANG Hua，YE Yanhui，et al.Robot Tracking of Vertical Welding Seam Based on Rotating Arc Sensor[J].Journal of Shanghai Jiao Tong University，2015，49(3):348-352.
[5]LIU S，WANG G，ZHANG H,et al.Design of Robot Welding Seam Tracking System with Structured Light Vision[J].Chinese Journal of Mechanical Engineering，2010，23(4):436-442.
[6]GAO X，YOU D，KATAYAMA S.Seam Tracking Monitoring Based on Adaptive Kalman Filter Embedded Elman Neural Network during High-power Fiber Laser Welding[J].IEEE Transactions on Industrial Electronics，2012，59(11):4315-4325.
[7]WANG Z.An Imaging and Measurement System for Robust Reconstruction of Weld Pool during Arc Welding[J].IEEE Transactions on Industrial Electronics，2015，62(8):5109-5118.
[8]KIM K B，WOO Y W，SONG D H，et al.Enhanced Image Binarization Using Intensity Range of Grayscale Images[J].International Journal of Multimedia & Ubiquitous Engineering，2015，10(7):139-144.
[9]CHEN Q，ZHAO L，LU J，et al.Modified Two-dimensional Otsu Image Segmentation Algorithm and Fast Realisation[J].IET Image Processing，2012，6(4):426-433.
[10]MOGHADDAM R F，CHERIET M.AdOtsu:an Adaptive and Parameterless Generalization of Otsu's Method for Document Image Binarization[J].Pattern Recognition，2012，45(6):2419-2431.
[11]LU N，SILVA J，YU G，et al.Directional Histogram Ratio at Random Probes:a Local Thresholding Criterion for Capillary Images[J].Pattern Recognition，2013，46(7):1933-1948.
[12]VALIZADEH M，KABIR E.Partitioning of Feature Space by Iterative Classification for Degraded Document Image Binarisation[J].IET Image Processing，2012，6(6):804-812.
[13]BELHEDI A，MARCOTEGUI B.Adaptive Scene-text Binarisation on Images Captured by Smartphones[J].IET Image Processing，2016，10(7):515-523.
[14]BERNSEN J.Dynamic Thresholding of Gray-level Images[J].Proceedings of the Eighth ICPR,1986(4):1251-1255.
[15]TALAB A M A，HUANG Zhangcan，WANG Junfei.An Enhanced Bernsen Algorithm Approaches for Vehicle Logo Detection[J].International Journal of Signal Processing Image Processing & P，2014，7(4):203-210.
[16]OSTU N. A Threshold Selection Method from Gray-level Histogram[J].IEEE Transactions on Systems,Man & Cybernetics，1979，9(1):62-66.
[17]LI Xinde，LI Xianghui，GE Shuzhi，et al.Automatic Welding Seam Tracking and Identification[J].IEEE Transactions on Industrial Electronics，2017，64(9):7261-7271.
[18]WU Q Q，LEE J P，PARK M H，et al.A Study on the Modified Hough Algorithm for Image Processing in Weld Seam Tracking[J].Journal of Mechanical Science & Technology，2015，29(11):4859-4865.
[19]申俊琦，胡绳荪，冯胜强.激光视觉焊缝跟踪中图像二值化处理[J].天津大学学报(自然科学与工程技术版)，2011，44(4):308-312.
SHEN Junqi，HU Shengsun，FENG Shengqiang.Image Binarization Processing in Laser Vision Seam Tracking[J].Journal of Tianjin University(Science and Technology)，2011，44(4):308-312.
[20]齐继阳，李金燕，陆震云,等.改进的Otsu法在焊接图像分割中的应用[J].焊接学报，2016，37(10):97-100.
QI Jiyang，LI Jinyan，LU Zhenyun，et al.Application of Improved Otsu Algorithm to Welding Image Segmentation[J].Transactions of the China Welding Institution，2016，37(10):97-100.
[21]刘哲.基于图像分析的织物外观质量综合评价[J].纺织学报，2012，33(11):61-65.
LIU Zhe.Comprehensive Evaluation of Appearance Quality of Fabrics Based on Image Analysis[J].Journal of Textile Research，2012，33(11):61-65.
[22]张鄂.现代设计方法[M].北京：高等教育出版社，2013:52-70.
ZHANG E.Advanced Design Methods[M].Beijing:China Machine Press，2013:52-70.