基于机器视觉的磨削表面粗糙度检测
|
摘要
表面粗糙度是反映零件表面上微观几何形状误差的一个重要指标,也是应用最为广泛的表征零件表面特性的参数。随着机械制造业的发展和检测技术的提高,许多科研组织都在十分活跃地深入研究表面粗糙度测量的各种关键技术,以实现表面粗糙度的快速无损检测。
本文综合比较了目前常用的几种表面粗糙度测量方法,针对磨削表面纹理随机性强,分布方向性不足等特点,结合机器视觉和神经网络技术,提出了一种新的表面粗糙度检测方法。以面信息代替传统测量中的线信息,并通过存储图像和数据资料,使表面粗糙度测量具有一定的可重复性。
本文首先深入分析了不同光源条件下磨削表面的图像特征,通过实验,优选LN-60聚光型LED线光源为磨削表面粗糙度检测用最佳光源,并构建了由体视显微镜、CCD摄像机、图像采集卡和LED光源等设备组成的表面粗糙度检测硬件系统。其次,以灰度变化轮廓曲线为依据,定量评定了各种滤波和图像增强方式对磨削表面图像的处理效果,开发了有效的图像预处理程序。并利用灰度级阈值化的分割处理,提出了磨削表面粗糙度测量前的缺陷检测算法,实现了缺陷质心位置的识别和缺陷面积等属性的计算。然后,采用二维离散傅里叶变换将磨削表面图像所呈现的纹理特征转换到频域中进一步加以分析,发现功率谱半径、平均功率谱和中心功率谱百分比与表面粗糙度值呈近似单调函数关系,故以这些特征量为输入,建立BP神经网络模型,完成了表面粗糙度值的测量,平均准确率可达93.8%,从而可实现在一定条件下,对传统接触式测量的替代。最后以LabVIEW为系统平台,辅以Visual C++和Matlab神经网络工具箱,开发了相应的磨削表面粗糙度检测软件。
Surface roughness is one of important indexes reflecting microscopic error in geometrical form. And also, it is a famous parameter which is used widely to represent characteristics of surface. As the industry of mechanical manufacturing and detection technology develop, many groups are making intensive studies of various key technologies actively to realize quick and nondestructive examination of surface roughness.
This thesis compared several ordinary measuring methods of surface roughness synthetically. Because the texture of ground surface displays strong randomness and insufficient directivity of distribution, a new detection method of surface roughness was put forward, through combination of computer vision and neural network technique. Roughness information of a line in traditional measurements would be replaced with information of a region by this method. And the survey of surface roughness implied a degree of repeatability, with memory of images and data information.
Firstly, this thesis analyzed image characteristics of ground surface under different light sources profoundly, and chose condensing LED line source, whose model was LN-60, to be optimal selection of ground surface assessment through experiments. Hence, hardware system of surface roughness detection was established by adopting body microscope, CCD camera, image acquisition card and LED light source. Secondly, assessing the effects of various filtering methods and image enhancement approaches quantitatively according to profile curves of grey variation, the thesis developed effective image pre-processing programs, and put forward an detection algorithm of surface defects applied before surface roughness measuring by utilizing image segmentation based on grey-level thresholding. Therefore, we could recognize mass centric positions of surface defects and calculate properties of them, such as area, and so on. Thirdly, this thesis transformed ground surface images into frequency domain adopting two-dimensional Discrete Fourier Transform in order to implement further texture characteristic analysis. Then we discovered that power spectral radius, average power spectrum and central power spectrum percentage had approximately monotone relationship with the value of roughness, so these characteristics were extracted as inputs of BP neural network model to accomplish measurement of surface roughness, and the average percentage of accurancy could reach 93.8%. Hence, traditional stylus method could be substituted with this model under cetain conditions. Finally, this thesis developed detection software of ground surface roughness, taking LabVIEW as system platform, Visual C++ and MATLAB Neural Network Toolbox as auxiliary tools.
本文综合比较了目前常用的几种表面粗糙度测量方法,针对磨削表面纹理随机性强,分布方向性不足等特点,结合机器视觉和神经网络技术,提出了一种新的表面粗糙度检测方法。以面信息代替传统测量中的线信息,并通过存储图像和数据资料,使表面粗糙度测量具有一定的可重复性。
本文首先深入分析了不同光源条件下磨削表面的图像特征,通过实验,优选LN-60聚光型LED线光源为磨削表面粗糙度检测用最佳光源,并构建了由体视显微镜、CCD摄像机、图像采集卡和LED光源等设备组成的表面粗糙度检测硬件系统。其次,以灰度变化轮廓曲线为依据,定量评定了各种滤波和图像增强方式对磨削表面图像的处理效果,开发了有效的图像预处理程序。并利用灰度级阈值化的分割处理,提出了磨削表面粗糙度测量前的缺陷检测算法,实现了缺陷质心位置的识别和缺陷面积等属性的计算。然后,采用二维离散傅里叶变换将磨削表面图像所呈现的纹理特征转换到频域中进一步加以分析,发现功率谱半径、平均功率谱和中心功率谱百分比与表面粗糙度值呈近似单调函数关系,故以这些特征量为输入,建立BP神经网络模型,完成了表面粗糙度值的测量,平均准确率可达93.8%,从而可实现在一定条件下,对传统接触式测量的替代。最后以LabVIEW为系统平台,辅以Visual C++和Matlab神经网络工具箱,开发了相应的磨削表面粗糙度检测软件。
Surface roughness is one of important indexes reflecting microscopic error in geometrical form. And also, it is a famous parameter which is used widely to represent characteristics of surface. As the industry of mechanical manufacturing and detection technology develop, many groups are making intensive studies of various key technologies actively to realize quick and nondestructive examination of surface roughness.
This thesis compared several ordinary measuring methods of surface roughness synthetically. Because the texture of ground surface displays strong randomness and insufficient directivity of distribution, a new detection method of surface roughness was put forward, through combination of computer vision and neural network technique. Roughness information of a line in traditional measurements would be replaced with information of a region by this method. And the survey of surface roughness implied a degree of repeatability, with memory of images and data information.
Firstly, this thesis analyzed image characteristics of ground surface under different light sources profoundly, and chose condensing LED line source, whose model was LN-60, to be optimal selection of ground surface assessment through experiments. Hence, hardware system of surface roughness detection was established by adopting body microscope, CCD camera, image acquisition card and LED light source. Secondly, assessing the effects of various filtering methods and image enhancement approaches quantitatively according to profile curves of grey variation, the thesis developed effective image pre-processing programs, and put forward an detection algorithm of surface defects applied before surface roughness measuring by utilizing image segmentation based on grey-level thresholding. Therefore, we could recognize mass centric positions of surface defects and calculate properties of them, such as area, and so on. Thirdly, this thesis transformed ground surface images into frequency domain adopting two-dimensional Discrete Fourier Transform in order to implement further texture characteristic analysis. Then we discovered that power spectral radius, average power spectrum and central power spectrum percentage had approximately monotone relationship with the value of roughness, so these characteristics were extracted as inputs of BP neural network model to accomplish measurement of surface roughness, and the average percentage of accurancy could reach 93.8%. Hence, traditional stylus method could be substituted with this model under cetain conditions. Finally, this thesis developed detection software of ground surface roughness, taking LabVIEW as system platform, Visual C++ and MATLAB Neural Network Toolbox as auxiliary tools.
引文
[1]郑焕文,蔡光起.国内外磨削技术的现状与主要发展方向[J].汽车工艺与材料,1999,5:1-5.
[2]王涛,李剑,高航.磨削技术的现状与发展趋势[J].机械设计与制造,2003,2:116-118.
[3]吴立群,杨将新,吴昭同.广义粗糙参数与性能关系系统分类研究[J].组合机床与自动化加工技术,1999,(11):19-21.
[4]王家忠,王龙山,周桂红.基于模糊基函数网络和自适应最小二乘算法的外圆纵向磨削表面粗糙度的预测[J].中国机械工程,2006,17(12):1223-1227.
[5]李国发,王龙山,丁宁.基于进化神经网络外圆纵向磨削表面粗糙度的在线预测[J].中国机械工程,2005,16(3):223-226.
[6]曾文涵,谢铁邦,蒋向前,等.表面粗糙度的稳健提取方法研究[J].中国机械工程,2004,15(2):127-130.
[7]蔡光起,冯宝富,赵恒华.磨削技术的最新进展[J].世界制造技术与装备市场,2003,1:16-19.
[8]HOY D E P,YU F.Surface quality assessment using computer vision methods[J].Journal of Materials Processing Technology,1991,28:265-274.
[9]袁长良,丁志华,武文堂.表面粗糙度及其测量[M].北京:机械工业出版社,1989:43-53.
[10]刘品,李哲.机械精度设计与检测基础[M].第四版.哈尔滨:哈尔滨工业大学出版社,2006:122.
[11]张国维.表面粗糙度测量的新方法[J].机床,1990,2:27-30.
[12]王爱囡.表面粗糙度在线识别的理论与实践[J].合肥工业大学学报:自然科学版,2004,27(4):425-429.
[13]BIGERELLE M,NAJJAR D.Relevance of roughness parameters for describing and modeling machined surfaces[J].Journal of Materials Science,2003,38(11):2525-2536.
[14]SCHMALTZ G.Technische oberflachenkunde[M].Berlin:Verlag J.Springer,1936:73-98.
[15]李满昌,程庆柱,李东.表面粗糙度新旧国家标准差异的分析[J].标准与 检测,2005,33(7):44-46.
[16]黄逸云.随机表面二阶谱矩和统计不变量的几何解释及其图解法[J].浙江大学学报:工学版,1985,(06):13-17.
[17]KLIMCZAK T,SLOWIKOWSKA H,SLOWIKOWSKA J.A winiarska contribution to the qualitative and quantitative estimation of the PD effect on the surface layer of epoxy resins and composites[C].The Seventh International Conference on Dielectric Materials,Measurements and Applications,USA,1996:338-341.
[18]DONG W P,SULLIVAN P J,STOUT K J.Comprehensive study of parameters for characterization 3D surface topography-Ⅲ[J].Wear,1994,178(1):29-43.
[19]DONG W P,SULLIVAN P J,STOUT K J.Comprehensive study of parameters for characterization 3D surface topography-Ⅳ[J].Wear,1994,178(1):45-60.
[20]SAYLES R S,THOMAS T R.Surface topography as a nonstationary random process[J].Nature,1978,271:431-434.
[21]强锡富.电动量仪(上)[M].北京:机械工业出版社,1983:14-53.
[22]TEAGUE E C,SCIRE F E.Three-dimension stylus profilometry[J].Wear,1982.83:1-12.
[23]竹田忠夫.表面形状的光学测量技术[J].光学精密机械,1987,(2):18-22.
[24]SOMMARGREN E G.Optical heterodyne profilometry[J].Applied Optics,1981,20(4):610-614.
[25]王更新.光学式表面粗糙度计测技术发展动向[J].航空计测技术,1994,14(3):39-43.
[26]陈晓梅.表面粗糙度干涉图像处理系统[J].航空计测技术,1997,17(3):7-10.
[27]张锡芳,王政平,王晓忠,等.基于共光路干涉原理的精细表面粗糙度测量方法[J].光学与光电技术,2006,4(5):74-84.
[28]王世华.轴承内外圈沟道激光表面粗糙度测量仪[J].工具技术,1998,32(7):40-42.
[29]王世华.激光表面粗糙度测量仪的研制[J].成都科技大学学报,1995,(3):62-66.
[30]WANG W,WONG P L,LUO J B,etc.A new optical technique for roughness measurement on moving surface[J].Tribology International,1998,31(5):281- 287.
[31]JOLIC K I,NAGARAJAH C R,THOMPSON W.Non-contact optically based measurement of surface roughness of ceramics[J].Measurement Science and Technology,1994,5:671-684.
[32]李博,黄镇昌,全燕鸣.光切法在动态表面粗糙度检测中的应用[J].微计算机信息,2007,(10):127-129.
[33]张泰昌.光切法测量表面粗糙度的常见问题与消除方法[J].机械工人,2005,(3):55-57.
[34]尤政.光外差干涉全光纤表面粗糙度传感器的研究[J].光学技术,1994,(6):45-47.
[35]陈晓梅.表面粗糙度干涉图像处理中的阈值优选[J].光学学报,1994,14(11):1183-1186.
[36]FERCHER A F.测量表面粗糙度形貌的双波长散斑干涉测量技术[J].国内外激光进展,1987,(1):52-54.
[37]邱瑜.用激光散射法非接触在线检测表面粗糙度[J].工具技术,2000,34(4):36-38.
[38]NOWICKI B,JARKIEWICZ A.The in-process surface roughness measurement using fringe field capacitive(FFC) method[J].International Journal of Machine Tools and Manufacture,1998,38(5-6):725-732.
[39]TSAI Y H,CHEN J C,LOU S J.An in-process surface recognition system based on neural networks in end milling cutting operations[J].International Journal of Machine Tools & Manufacture,1999,39(4):583-605.
[40]AZOUZI R,GUILLOT M.On-line prediction of surface finish and dimensional deviation in turning using neural network based sensor fusion[J].Tools Manufact,1997,37(9):1201-1217.
[41]段峰,王耀南,雷晓峰,等.机器视觉技术及其应用综述[J].自动化博览,2002,3:59-61.
[42]葛云涛.机器视觉光学基础[EB/OL].西安:中美合资西安丰唐光电科技有限公司,2004.http://www.photonscope.com.
[43]杨明,白烨,王秋良,等.面阵CCD摄像机光学镜头参数及选用[J].光电子技术与信息,2005,18(3):27-30.
[44]周太明.高效照明系统设计指南[M].上海:复旦大学出版社,2004:21-35.
[45]薛得风.基于图形化编程语言LabVIEW的一种虚拟仪器的实现[J].自动化与仪器仪表,2003:24-26.
[46]张毅,周绍磊,杨秀霞.虚拟仪器技术分析与应用[M].北京:机械工业出版社,2004:300-321.
[47]国科学院数学研究所数理统计组.正交试验法[M].北京:人民教育出版社,1975:136-152.
[48]李庆震,祝小平.基于核PCA的智能图像分析算法[J].弹箭与制导学报,2007,27(5):189-192.
[49]章毓晋.图像工程(下册)--图像理解与计算机视觉[M].北京:清华大学出版社,2000:65-70.
[50]王明泉,韩焱.非线性滤波在射线图像降噪增强中的应用[J].无损检测,2002,24(7):281-285.
[51]杨平先,孙兴波,干树川.一种改进的数学形态学图像滤波算法[J].华北电力大学学报,2005,32(6):56-59.
[52]许景波,袁怡宝,朴伟英,等.表面粗糙度测量中的高斯滤波快速算法[J].计量学报,2005,26(4):310-312.
[53]许景波,袁怡宝,朴伟英,等.减小表面粗糙度测量高斯滤波幅度偏差[J].机械工程学报,2006,42(4):42-46.
[54]隋东坡,周焰,肖志坚.基于粗糙度的改进Canny边缘检测方法[J].计算机工程与应用,2005,9:37-39.
[55]CHAPPARD D.Image analysis measurements of roughness by texture and fractal analysis correlate with contact profilometry[J].Biomaterials,2003,24:1399-1407.
[56]KASSIM A A,MANNAN M A,JING M.Machine tool condition monitoring using workpiece surface texture analysis[J].Machine Vision and Applications,2000,11:257-263.
[57]胡金华.工件表面纹理分析方法研究[J].浙江工贸职业技术学院学报,2005,5(4):49-52.
[58]BOUZID W,TSOUMAREV O.An investigation of surface roughness of burnished AISI 1042 steel[J].Int J Adv ManufTechnol,2004,24:120-125.
[59]LEE B Y,YU S F,JUAN H.The Model of surface roughness inspection by vision system in turning[J].Mechatronics,2004,14(1):129-141.
[60]KUMAR R.Application of digital image magnification for surface roughness evaluation using machine vision[J].International Journal of Machine Tools and Manufacture,2005,45(2):228-234.
[61]马聪,黎明,王长坤.机械加工表面粗糙度的视觉检测[J].南昌航空工业学院学报:自然科学版,2003,17(3):88-94.
[62]朱铮涛,黎绍发.基于机器视觉的零件表面粗糙度测量[J].仪器仪表与检测,2002,(8):46-47.
[63]徐贵力,毛罕平.利用傅里叶变换提取图像纹理特征新方法[J].光电工程,2004,31(11):55-58.
[64]王文发,刘彦保.傅里叶变换用于图像处理时的特性分析[J].延安大学学报:自然科学版,2006,25(23):22-24.
[65]SONKA M,HLAVAC V,BOYLE R.Image processing,analysis,and machine vision[M].Second Edition.USA:Thomson Learning and PT Press,1999:85-121.
[66]HO S Y,LEE K C.Accurate modeling and prediction of surface roughness by computer vision in turning operations using an adaptive neural-fuzzy inference system[J].International Journal of Machine Tools and Manufacture,2002,42(13):1441-1446.
[67]LEE K C,HO S Y.Accurate estimation of surface roughness from texture features of the surface image using an adaptive neural-fuzzy inference system[J].Precision Engineering,2005,29(1):95-100.
[68]FREDJ N B,AMAMOU R.Ground surface roughness prediction based upon experimental design and neural network models[J].Int J Adv Manuf Technol,2006,31:24-36.
[69]张永宏,胡德金,张凯,等.基于进化神经网络的曲面磨削表面粗糙度预测[J].上海交通大学学报,2005,39(3):373-376.
[2]王涛,李剑,高航.磨削技术的现状与发展趋势[J].机械设计与制造,2003,2:116-118.
[3]吴立群,杨将新,吴昭同.广义粗糙参数与性能关系系统分类研究[J].组合机床与自动化加工技术,1999,(11):19-21.
[4]王家忠,王龙山,周桂红.基于模糊基函数网络和自适应最小二乘算法的外圆纵向磨削表面粗糙度的预测[J].中国机械工程,2006,17(12):1223-1227.
[5]李国发,王龙山,丁宁.基于进化神经网络外圆纵向磨削表面粗糙度的在线预测[J].中国机械工程,2005,16(3):223-226.
[6]曾文涵,谢铁邦,蒋向前,等.表面粗糙度的稳健提取方法研究[J].中国机械工程,2004,15(2):127-130.
[7]蔡光起,冯宝富,赵恒华.磨削技术的最新进展[J].世界制造技术与装备市场,2003,1:16-19.
[8]HOY D E P,YU F.Surface quality assessment using computer vision methods[J].Journal of Materials Processing Technology,1991,28:265-274.
[9]袁长良,丁志华,武文堂.表面粗糙度及其测量[M].北京:机械工业出版社,1989:43-53.
[10]刘品,李哲.机械精度设计与检测基础[M].第四版.哈尔滨:哈尔滨工业大学出版社,2006:122.
[11]张国维.表面粗糙度测量的新方法[J].机床,1990,2:27-30.
[12]王爱囡.表面粗糙度在线识别的理论与实践[J].合肥工业大学学报:自然科学版,2004,27(4):425-429.
[13]BIGERELLE M,NAJJAR D.Relevance of roughness parameters for describing and modeling machined surfaces[J].Journal of Materials Science,2003,38(11):2525-2536.
[14]SCHMALTZ G.Technische oberflachenkunde[M].Berlin:Verlag J.Springer,1936:73-98.
[15]李满昌,程庆柱,李东.表面粗糙度新旧国家标准差异的分析[J].标准与 检测,2005,33(7):44-46.
[16]黄逸云.随机表面二阶谱矩和统计不变量的几何解释及其图解法[J].浙江大学学报:工学版,1985,(06):13-17.
[17]KLIMCZAK T,SLOWIKOWSKA H,SLOWIKOWSKA J.A winiarska contribution to the qualitative and quantitative estimation of the PD effect on the surface layer of epoxy resins and composites[C].The Seventh International Conference on Dielectric Materials,Measurements and Applications,USA,1996:338-341.
[18]DONG W P,SULLIVAN P J,STOUT K J.Comprehensive study of parameters for characterization 3D surface topography-Ⅲ[J].Wear,1994,178(1):29-43.
[19]DONG W P,SULLIVAN P J,STOUT K J.Comprehensive study of parameters for characterization 3D surface topography-Ⅳ[J].Wear,1994,178(1):45-60.
[20]SAYLES R S,THOMAS T R.Surface topography as a nonstationary random process[J].Nature,1978,271:431-434.
[21]强锡富.电动量仪(上)[M].北京:机械工业出版社,1983:14-53.
[22]TEAGUE E C,SCIRE F E.Three-dimension stylus profilometry[J].Wear,1982.83:1-12.
[23]竹田忠夫.表面形状的光学测量技术[J].光学精密机械,1987,(2):18-22.
[24]SOMMARGREN E G.Optical heterodyne profilometry[J].Applied Optics,1981,20(4):610-614.
[25]王更新.光学式表面粗糙度计测技术发展动向[J].航空计测技术,1994,14(3):39-43.
[26]陈晓梅.表面粗糙度干涉图像处理系统[J].航空计测技术,1997,17(3):7-10.
[27]张锡芳,王政平,王晓忠,等.基于共光路干涉原理的精细表面粗糙度测量方法[J].光学与光电技术,2006,4(5):74-84.
[28]王世华.轴承内外圈沟道激光表面粗糙度测量仪[J].工具技术,1998,32(7):40-42.
[29]王世华.激光表面粗糙度测量仪的研制[J].成都科技大学学报,1995,(3):62-66.
[30]WANG W,WONG P L,LUO J B,etc.A new optical technique for roughness measurement on moving surface[J].Tribology International,1998,31(5):281- 287.
[31]JOLIC K I,NAGARAJAH C R,THOMPSON W.Non-contact optically based measurement of surface roughness of ceramics[J].Measurement Science and Technology,1994,5:671-684.
[32]李博,黄镇昌,全燕鸣.光切法在动态表面粗糙度检测中的应用[J].微计算机信息,2007,(10):127-129.
[33]张泰昌.光切法测量表面粗糙度的常见问题与消除方法[J].机械工人,2005,(3):55-57.
[34]尤政.光外差干涉全光纤表面粗糙度传感器的研究[J].光学技术,1994,(6):45-47.
[35]陈晓梅.表面粗糙度干涉图像处理中的阈值优选[J].光学学报,1994,14(11):1183-1186.
[36]FERCHER A F.测量表面粗糙度形貌的双波长散斑干涉测量技术[J].国内外激光进展,1987,(1):52-54.
[37]邱瑜.用激光散射法非接触在线检测表面粗糙度[J].工具技术,2000,34(4):36-38.
[38]NOWICKI B,JARKIEWICZ A.The in-process surface roughness measurement using fringe field capacitive(FFC) method[J].International Journal of Machine Tools and Manufacture,1998,38(5-6):725-732.
[39]TSAI Y H,CHEN J C,LOU S J.An in-process surface recognition system based on neural networks in end milling cutting operations[J].International Journal of Machine Tools & Manufacture,1999,39(4):583-605.
[40]AZOUZI R,GUILLOT M.On-line prediction of surface finish and dimensional deviation in turning using neural network based sensor fusion[J].Tools Manufact,1997,37(9):1201-1217.
[41]段峰,王耀南,雷晓峰,等.机器视觉技术及其应用综述[J].自动化博览,2002,3:59-61.
[42]葛云涛.机器视觉光学基础[EB/OL].西安:中美合资西安丰唐光电科技有限公司,2004.http://www.photonscope.com.
[43]杨明,白烨,王秋良,等.面阵CCD摄像机光学镜头参数及选用[J].光电子技术与信息,2005,18(3):27-30.
[44]周太明.高效照明系统设计指南[M].上海:复旦大学出版社,2004:21-35.
[45]薛得风.基于图形化编程语言LabVIEW的一种虚拟仪器的实现[J].自动化与仪器仪表,2003:24-26.
[46]张毅,周绍磊,杨秀霞.虚拟仪器技术分析与应用[M].北京:机械工业出版社,2004:300-321.
[47]国科学院数学研究所数理统计组.正交试验法[M].北京:人民教育出版社,1975:136-152.
[48]李庆震,祝小平.基于核PCA的智能图像分析算法[J].弹箭与制导学报,2007,27(5):189-192.
[49]章毓晋.图像工程(下册)--图像理解与计算机视觉[M].北京:清华大学出版社,2000:65-70.
[50]王明泉,韩焱.非线性滤波在射线图像降噪增强中的应用[J].无损检测,2002,24(7):281-285.
[51]杨平先,孙兴波,干树川.一种改进的数学形态学图像滤波算法[J].华北电力大学学报,2005,32(6):56-59.
[52]许景波,袁怡宝,朴伟英,等.表面粗糙度测量中的高斯滤波快速算法[J].计量学报,2005,26(4):310-312.
[53]许景波,袁怡宝,朴伟英,等.减小表面粗糙度测量高斯滤波幅度偏差[J].机械工程学报,2006,42(4):42-46.
[54]隋东坡,周焰,肖志坚.基于粗糙度的改进Canny边缘检测方法[J].计算机工程与应用,2005,9:37-39.
[55]CHAPPARD D.Image analysis measurements of roughness by texture and fractal analysis correlate with contact profilometry[J].Biomaterials,2003,24:1399-1407.
[56]KASSIM A A,MANNAN M A,JING M.Machine tool condition monitoring using workpiece surface texture analysis[J].Machine Vision and Applications,2000,11:257-263.
[57]胡金华.工件表面纹理分析方法研究[J].浙江工贸职业技术学院学报,2005,5(4):49-52.
[58]BOUZID W,TSOUMAREV O.An investigation of surface roughness of burnished AISI 1042 steel[J].Int J Adv ManufTechnol,2004,24:120-125.
[59]LEE B Y,YU S F,JUAN H.The Model of surface roughness inspection by vision system in turning[J].Mechatronics,2004,14(1):129-141.
[60]KUMAR R.Application of digital image magnification for surface roughness evaluation using machine vision[J].International Journal of Machine Tools and Manufacture,2005,45(2):228-234.
[61]马聪,黎明,王长坤.机械加工表面粗糙度的视觉检测[J].南昌航空工业学院学报:自然科学版,2003,17(3):88-94.
[62]朱铮涛,黎绍发.基于机器视觉的零件表面粗糙度测量[J].仪器仪表与检测,2002,(8):46-47.
[63]徐贵力,毛罕平.利用傅里叶变换提取图像纹理特征新方法[J].光电工程,2004,31(11):55-58.
[64]王文发,刘彦保.傅里叶变换用于图像处理时的特性分析[J].延安大学学报:自然科学版,2006,25(23):22-24.
[65]SONKA M,HLAVAC V,BOYLE R.Image processing,analysis,and machine vision[M].Second Edition.USA:Thomson Learning and PT Press,1999:85-121.
[66]HO S Y,LEE K C.Accurate modeling and prediction of surface roughness by computer vision in turning operations using an adaptive neural-fuzzy inference system[J].International Journal of Machine Tools and Manufacture,2002,42(13):1441-1446.
[67]LEE K C,HO S Y.Accurate estimation of surface roughness from texture features of the surface image using an adaptive neural-fuzzy inference system[J].Precision Engineering,2005,29(1):95-100.
[68]FREDJ N B,AMAMOU R.Ground surface roughness prediction based upon experimental design and neural network models[J].Int J Adv Manuf Technol,2006,31:24-36.
[69]张永宏,胡德金,张凯,等.基于进化神经网络的曲面磨削表面粗糙度预测[J].上海交通大学学报,2005,39(3):373-376.