基于视觉测量的齿廓图像边缘失真判别算法
|
摘要
针对齿轮视觉测量过程中因齿廓表面受到污染导致齿廓图像边缘出现光学失真,从而影响齿廓偏差、齿距偏差测量精度问题,提出一种基于视觉测量的齿廓图像边缘失真迭代逼近——临近度判别算法(IAPD).建立渐开线齿廓图像边缘过渡带内像素点法向偏距与像素点极径的映射关系,将复杂的二维图像边缘信号转化为容易处理的一维信号;利用小波去噪算法对信号进行处理,提取齿廓边缘的失真特征;采用变阈值迭代逼近算法分离出齿廓倾斜偏差;采用K-邻近度分类方法自动判别齿廓图像边缘失真的起止位置,为齿距、齿廓偏差测量时进行齿廓图像边缘失真修正提供定位依据.为验证本算法的可靠性,根据相邻同名齿廓真实边缘的相似性,对失真齿廓和无失真齿廓图像提取亚像素边缘,并进行相似性比较,实现基于相似性比较的齿廓图像边缘失真判别算法,以此对IAPD算法的失真区域判别精度进行校验.实验结果表明:本文提出的齿廓图像边缘失真判别算法能够快速自动识别图像失真区域,失真区域边界的径向定位精度可以达到2.5个像素(50μm),能够满足图像边缘失真修正补偿的定位精度要求,可以实现齿轮测量的实时计算.
The problem of optical distortion caused by the contamination of the toothed gear profile surface was studied which affects the accuracy of measurement on the toothed gear profile deviation and the pitch deviation.Iterative Approximation-Proximity Discrimination algorithm(IAPD)using visual measurement is proposed to determine the image edge distortion of the toothed gear profile.The algorithm constructs the mapping relationship between the normal pixel offset in the edge transition zone of the involute profile image and the polar diameter of the pixel.This mapping converts the complex twodimensional image edge signal into a one-dimensional signal,which is easier to process.The wavelet denoising algorithm was used to process the signal to extract the distortion features of the toothed gear profile edge,and the variable threshold iterative fitting algorithm was used to separate the toothed gear profile tilt deviation.According to the reasonable range of the normal toothed gear profile error,Kproximity classification method is adopted.The starting and ending position of the edge distortion of the toothed gear profile image is determined,and the positioning basis is provided for correcting the edge distortion of the toothed gear profile image during the measurement of the pitch and the toothed gear profile deviation.In order to verify the reliability of the IAPD algorithm,according to the similarity of the real edges of adjacent ipsilateral tooth profiles,the sub-pixel edges are extracted from the distortion tooth profile and the distortion-free tooth profile image,and similarity comparison is performed to realize the profile edge similarity comparison algorithm of distortion region recognition.The algorithm is used to verify the distortion region discrimination accuracy of the IAPD algorithm.The experimental results show that the toothed gear profile image edge distortion detecting algorithm can identify the image distortion region with good accuracy.The accuracy of radial range of the distortion region can reach 2.5 pixels(50μm),which can meet the requirement of the image edge distortion correction.In addition,the algorithm is easy to understand and highly effective,which is easy to deploy and can meet the requirements of real-time calculation during gear measurement.
The problem of optical distortion caused by the contamination of the toothed gear profile surface was studied which affects the accuracy of measurement on the toothed gear profile deviation and the pitch deviation.Iterative Approximation-Proximity Discrimination algorithm(IAPD)using visual measurement is proposed to determine the image edge distortion of the toothed gear profile.The algorithm constructs the mapping relationship between the normal pixel offset in the edge transition zone of the involute profile image and the polar diameter of the pixel.This mapping converts the complex twodimensional image edge signal into a one-dimensional signal,which is easier to process.The wavelet denoising algorithm was used to process the signal to extract the distortion features of the toothed gear profile edge,and the variable threshold iterative fitting algorithm was used to separate the toothed gear profile tilt deviation.According to the reasonable range of the normal toothed gear profile error,Kproximity classification method is adopted.The starting and ending position of the edge distortion of the toothed gear profile image is determined,and the positioning basis is provided for correcting the edge distortion of the toothed gear profile image during the measurement of the pitch and the toothed gear profile deviation.In order to verify the reliability of the IAPD algorithm,according to the similarity of the real edges of adjacent ipsilateral tooth profiles,the sub-pixel edges are extracted from the distortion tooth profile and the distortion-free tooth profile image,and similarity comparison is performed to realize the profile edge similarity comparison algorithm of distortion region recognition.The algorithm is used to verify the distortion region discrimination accuracy of the IAPD algorithm.The experimental results show that the toothed gear profile image edge distortion detecting algorithm can identify the image distortion region with good accuracy.The accuracy of radial range of the distortion region can reach 2.5 pixels(50μm),which can meet the requirement of the image edge distortion correction.In addition,the algorithm is easy to understand and highly effective,which is easy to deploy and can meet the requirements of real-time calculation during gear measurement.
引文
[1]LI Min-hua,BAI Meng,LV Ying-jun.Adaptive thresholding based edge detection approach for images[J].Pattern Recognition and Artificial Intelligence,2016,29(16):177-184.李敏花,柏猛,吕英俊.自适应阈值图像边缘检测方法[J].模式识别与人工智能,2016,29(16):177-184.
[2]SUN Wei-feng,HE Jun-hua.A new image de-noising method based on multiwavelet transform[J].Acta Photonica Sinica,2008,37(11):2360-2364.孙伟峰,何俊华.基于多小波变换的图像去噪新方法[J].光子学报,2008,37(11):2360-2364.
[3]LUO Jin-hua,JIANG Jin-peng,ZHU Pei-min.Automatic extraction of the side-scan sonar imagery outlines based on mathematical morphology[J].Haiyang Xuebao,2016,38(5):150-157.罗进华,蒋锦朋,朱培民.基于数学形态学的侧扫声呐图像轮廓自动提取[J].海洋学报,2016,38(5):150-157.
[4]WANG Jun-ping,HAO Yue.Boundary extraction based on morphology and size-shape measurement for the IC real defect[J].Chinese Journal of Computers,2000,23(7):673-678.王俊平,郝跃.IC真实缺陷的边界提取和缺陷尺寸与形状的表征[J].计算机学报,2000,23(7):673-678.
[5]WEN Wu,WEI Min,HE Jia.Highlight the image edge based on curve fitting[J].Journal of Chengdu University of Information Technology,2016,31(5):453-457.文武,魏敏,何嘉.基于曲线拟合的图像边缘突出显示[J].成都信息工程大学学报,2016,31(5):453-457.
[6]WANG Ning.Research on gear vision measurement system and tooth profile measurement technology[D].Shenyang:Shenyang University of Technology,2017:89-92.王宁.齿轮视觉测量系统与齿廓测量技术研究[D].沈阳:沈阳工业大学,2017:89-92.
[7]ZHI Shan,ZHAO Wen-zhen,ZHAO Wen-hui,et al.The visual measurement method of pitch machine based on the part of gear image[J].Chinese Journal of Scientific Instrument,2018,39(2):225-231.支珊,赵文珍,赵文辉,等.基于齿轮局部图像的齿距机器视觉测量方法[J].仪器仪表学报,2018,39(2):225-231.
[8]LIU Ming-cai.Wavelet analysis and its application[M].2nd ed.Beijing:Tsinghua University Press,2013:152-154.刘明才.小波分析及其应用(第2版)[M].北京:清华大学出版社,2013:152-154.
[9]QIU Zu-rong,SHI Zhao-yao,LI Yan.Research on the development of measurement technology mechanical manufacture[J].Journal of Mechanical Engineering,2010,46(14):1-11.裘祖荣,石照耀,李岩.机械制造领域测量技术的发展研究[J].机械工程学报,2010,46(14):1-11.
[10]ZHANG Ling-ling,XIAO Jing.Case study of mechanical fault diagnosis technology based on MATLAB[M].Beijing:Higher education press,2016.张玲玲,肖静.基于MATLAB的机械故障诊断技术案例教程[M].北京:高等教育出版社,2016.
[11]SUN Xian-ming,LIU Huan,ZHAO Xin-guang,et al.Singular point recognition and feature extraction for incipient bearing fault based on instantaneous envelope scalogram entropy[J].Journal of Mechanical Engineering,2017,53(3):73-80.孙鲜明,刘欢,赵新光,等.基于瞬时包络尺度谱熵的滚动轴承早期故障奇异点识别及特征提取[J].机械工程学报,2017,53(3):73-80.
[12]PIERRE B,PASCAL W,JACQUES D,et al.Potential volcanological applications of the DORIS system:ageodetic study of the Socorro Island(Mexico)coordinate time-series[J].Geophysical Journal International,2009,178(1):581-590.
[13]ZHAO Xue-zhi,LIN Ying,CHEN Wen-ge,et al.The choice of wavelet bases for singular signal deteetion[J].Journal of South China University of Technology(Natural Science Edition),2000,28(10):75-80.赵学智,林颖,陈文戈,等.奇异性信号检测时小波基的选择[J].华南理工大学学报(自然科学版),2000,28(10):75-80.
[14]WANG Ping,LI Xiang,MA Nan.Electric well logs de-noising based on thecuBic center Bspline wavelet[J].Computers and Applied Chemist,2009,26(4):417-424.王萍,李想,马楠.基于三次中心B样条小波的电测井信号去噪[J].计算机与应用化学,2009,26(4):417-424.
[15]MAO Ya-chun,WANG En-de,XIU Chun-hua.Data jump method:a new approach to eliminating the deformation monitoring data with gross errors[J].Journal of Northeastern University(Natural Science),2011,32(7):1020-1023.毛亚纯,王恩德,修春华.剔除变形监测粗差数据的新方法---数据跳跃法[J].东北大学学报(自然科学版),2011,32(7):1020-1023.
[16]WANG Ning,DUAN Zhen-yun,ZHAO Wen-hui,et al.Algorithm of edge detection based on bertrand surface model[J].Acta Photonica Sinica,2017,46(10):1012003.王宁,段振云,赵文辉,等.基于Bertrand曲面模型的边缘检测算法[J].光子学报,2017,46(10):1012003.
[2]SUN Wei-feng,HE Jun-hua.A new image de-noising method based on multiwavelet transform[J].Acta Photonica Sinica,2008,37(11):2360-2364.孙伟峰,何俊华.基于多小波变换的图像去噪新方法[J].光子学报,2008,37(11):2360-2364.
[3]LUO Jin-hua,JIANG Jin-peng,ZHU Pei-min.Automatic extraction of the side-scan sonar imagery outlines based on mathematical morphology[J].Haiyang Xuebao,2016,38(5):150-157.罗进华,蒋锦朋,朱培民.基于数学形态学的侧扫声呐图像轮廓自动提取[J].海洋学报,2016,38(5):150-157.
[4]WANG Jun-ping,HAO Yue.Boundary extraction based on morphology and size-shape measurement for the IC real defect[J].Chinese Journal of Computers,2000,23(7):673-678.王俊平,郝跃.IC真实缺陷的边界提取和缺陷尺寸与形状的表征[J].计算机学报,2000,23(7):673-678.
[5]WEN Wu,WEI Min,HE Jia.Highlight the image edge based on curve fitting[J].Journal of Chengdu University of Information Technology,2016,31(5):453-457.文武,魏敏,何嘉.基于曲线拟合的图像边缘突出显示[J].成都信息工程大学学报,2016,31(5):453-457.
[6]WANG Ning.Research on gear vision measurement system and tooth profile measurement technology[D].Shenyang:Shenyang University of Technology,2017:89-92.王宁.齿轮视觉测量系统与齿廓测量技术研究[D].沈阳:沈阳工业大学,2017:89-92.
[7]ZHI Shan,ZHAO Wen-zhen,ZHAO Wen-hui,et al.The visual measurement method of pitch machine based on the part of gear image[J].Chinese Journal of Scientific Instrument,2018,39(2):225-231.支珊,赵文珍,赵文辉,等.基于齿轮局部图像的齿距机器视觉测量方法[J].仪器仪表学报,2018,39(2):225-231.
[8]LIU Ming-cai.Wavelet analysis and its application[M].2nd ed.Beijing:Tsinghua University Press,2013:152-154.刘明才.小波分析及其应用(第2版)[M].北京:清华大学出版社,2013:152-154.
[9]QIU Zu-rong,SHI Zhao-yao,LI Yan.Research on the development of measurement technology mechanical manufacture[J].Journal of Mechanical Engineering,2010,46(14):1-11.裘祖荣,石照耀,李岩.机械制造领域测量技术的发展研究[J].机械工程学报,2010,46(14):1-11.
[10]ZHANG Ling-ling,XIAO Jing.Case study of mechanical fault diagnosis technology based on MATLAB[M].Beijing:Higher education press,2016.张玲玲,肖静.基于MATLAB的机械故障诊断技术案例教程[M].北京:高等教育出版社,2016.
[11]SUN Xian-ming,LIU Huan,ZHAO Xin-guang,et al.Singular point recognition and feature extraction for incipient bearing fault based on instantaneous envelope scalogram entropy[J].Journal of Mechanical Engineering,2017,53(3):73-80.孙鲜明,刘欢,赵新光,等.基于瞬时包络尺度谱熵的滚动轴承早期故障奇异点识别及特征提取[J].机械工程学报,2017,53(3):73-80.
[12]PIERRE B,PASCAL W,JACQUES D,et al.Potential volcanological applications of the DORIS system:ageodetic study of the Socorro Island(Mexico)coordinate time-series[J].Geophysical Journal International,2009,178(1):581-590.
[13]ZHAO Xue-zhi,LIN Ying,CHEN Wen-ge,et al.The choice of wavelet bases for singular signal deteetion[J].Journal of South China University of Technology(Natural Science Edition),2000,28(10):75-80.赵学智,林颖,陈文戈,等.奇异性信号检测时小波基的选择[J].华南理工大学学报(自然科学版),2000,28(10):75-80.
[14]WANG Ping,LI Xiang,MA Nan.Electric well logs de-noising based on thecuBic center Bspline wavelet[J].Computers and Applied Chemist,2009,26(4):417-424.王萍,李想,马楠.基于三次中心B样条小波的电测井信号去噪[J].计算机与应用化学,2009,26(4):417-424.
[15]MAO Ya-chun,WANG En-de,XIU Chun-hua.Data jump method:a new approach to eliminating the deformation monitoring data with gross errors[J].Journal of Northeastern University(Natural Science),2011,32(7):1020-1023.毛亚纯,王恩德,修春华.剔除变形监测粗差数据的新方法---数据跳跃法[J].东北大学学报(自然科学版),2011,32(7):1020-1023.
[16]WANG Ning,DUAN Zhen-yun,ZHAO Wen-hui,et al.Algorithm of edge detection based on bertrand surface model[J].Acta Photonica Sinica,2017,46(10):1012003.王宁,段振云,赵文辉,等.基于Bertrand曲面模型的边缘检测算法[J].光子学报,2017,46(10):1012003.