基于Hough变换和GLCM的端铣表面粗糙度检测
|
摘要
研究基于计算机视觉的非接触式端铣表面粗糙度检测方法。通过图像采集系统获取端铣工件表面图像,并进行图像预处理。基于Hough变换旋转图像,提取特定方向下GLCM的特征参数,较大程度缩短了计算时间。确定了适于表征端铣表面粗糙度的4个GLCM特征参数。采用BP神经网络算法研究纹理特征参数与粗糙度Ra之间的关系,构建粗糙度BP神经网络检测模型。实验表明,基于Hough变换的GLCM纹理特征参数提取方法能快速实现粗糙度纹理特征的提取,而BP神经网络检测模型具有较好的预测效果,能够满足端铣表面粗糙度测量的精度要求。
A non-contact roughness measurement method of the face milling surface is studied in this paper,which is based on computer vision theory. The face milling surface image is obtained by the image collection system and is preprocessed. Using Hough transform, the image is rotated to ensure the texture direction is vertical downward. Therefore, we can compute GLCM texture parameters only on this single direction, thus the computing time is saved greatly. The four GLCM texture parameters are extracted as the roughness characteristics of face milling surface. BP neural network is used to model the relations between the GLCM texture parameters and the roughness Ra, and the roughness detection model of face milling surface is established. The experiment results showed that using GLCM based on Hough transform can extract the roughness texture parameters quickly. The BP network model can measure the roughness of face milling surface precisely.
A non-contact roughness measurement method of the face milling surface is studied in this paper,which is based on computer vision theory. The face milling surface image is obtained by the image collection system and is preprocessed. Using Hough transform, the image is rotated to ensure the texture direction is vertical downward. Therefore, we can compute GLCM texture parameters only on this single direction, thus the computing time is saved greatly. The four GLCM texture parameters are extracted as the roughness characteristics of face milling surface. BP neural network is used to model the relations between the GLCM texture parameters and the roughness Ra, and the roughness detection model of face milling surface is established. The experiment results showed that using GLCM based on Hough transform can extract the roughness texture parameters quickly. The BP network model can measure the roughness of face milling surface precisely.
引文
[1] J. P. Costes, V. Moreau. Surface Roughness Prediction in Milling Based on Tool Displacements[J]. Journal of Manufacturing Processes,2011, 13(2):133-140.
[2]曾泉人,刘更,刘岚.机械加工零件表面完整性表征模型研究[J].中国机械工程,2010,21(24):2995-2999.Zeng Q R, Liu G, Liu L. Quantitative Description Model of Surface integrity for Machined Parts[J]. China Mechanical Engineering,2010,21(24):2995-2999.
[3]李力,王耀南,陈铁健.大尺寸LCD玻璃基板多视觉缺陷检测系统研究[J].控制工程.2016, 23(2):222-226.LI L, Wang Y N, Chen T J. Multi-visual Detect System for Large-size LCD Glass Substrate[J]. Control Engineering of China.2016, 23(10)1519-1522.
[4] E.S.Gadelmawla. A Vision System for Surface Roughness Characterization Using the Gray Level Co-occurrence Matrix[J]. NDT and E International, 2004, 7(7):577-588.
[5]张建.基于图像法的工件表面粗糙度检测系统研究[D].南京:南京航空航天大学,2011:10-30.Zhang J. Surface Roughness Measurement System Based on Image Method[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2011:10-30.
[6]郑秀艳.基于显微视觉的深孔微异型面粗糙度测量方法[D].大连:大连理工大学,2012:37-51.Zheng X Y. A Roughness Measurement Method Based on Micro-Vision for Micro-Heterogeneous Surface in Deep Hole[D].DaLian.Dalian University of Technology, 2012:37-51.)Haralick R M, Shanmugam K. Texture Features for Image Classification[J].IEEE Transactions on Systems, Man, and Cybernetics, 1973, 3(06):6102-6211.
[7]田欣利,王健全,张保国,等.基于纹理分析的Si3N4陶瓷表面粗糙度研究[J].材料工程,2012,12(9):7-13.Tian X L, Wang J Q, Zhang B Q. Surface rouughness of Si3N4 based on texture anlysis[J]. Journal of Materials Engineering. 2012,12(9):7-13.
[8]高程程,惠晓威.基于灰度共生矩阵的纹理特征提取[J].计算机系统应用,2010,19(6):195-198.Gao.C.C,, Hui X W. GLCM-based texture feature extration[J].Computer systems&Applications, 2010,19(6):195-198
[9]龚昌来,杨冬涛.一种改进的双线性插值图像放大算法[J].激光与红外,2009,39(8):899-901.Gong L L, Yang D T:Improved Image Zooming Algorithm Based on Bilinear Interpolation[J]. LASER&INFRARED.2009,39(8):899-901.
[10]张振杰,郝向阳,刘松林,程传奇.基于Hough一维变换的直线检测算法[J].光学学报,2016,36(4):1-8.Zhang Z J, Hao X Y, Liu S L, Cheng C Q.Line detction Based on Hough One-Dimensional Transform[J]. Acta Optica sinica,2016,36(4):1-8
[11] Duda R O, Hart P E. Use of the Hough transformation to detect lines and curves in pictures[J]. Communications of the Association for Computing Machinery, 1972,15(1):11-15.
[12] Chung Kuo-Liang, Huang Yong-Huai, Tsai Shiang-Ren.Orientation-based discrete Hough transform for line detection with low computational complexity[J]. Applied Mathematics and Computation, 2014,237:430-437.
[13]刘鳍洁,陈桂明,刘小方,等.BP神经网络权重和阈值初始化方法研究[J].西南师范大学学报(自然科学版).2010, 35(6):137-141.Liu Q J, Chen G M, Liu X F, et al.:Research on Initialization Algorithms of Weights and Biases of BP Neural Network[J]. Journal of Southwest China Normal University(Natural Science Edition).2010,35(6):137-141.
[14] Biswajeet Pradhan, Ahmed M. Youssef, Renuganth Varathrajoo.Approaches for Delineating Landslide Hazard Areas Using Different Training Sites in an Advanced Artificial Neural Network Model[J].Geo-Spatial Information Science,2010,02:93-102.
[15]孙金根,张颖,张嘉男,赵忠兴.基于BP神经网络的铝液夹杂物预测[J].控制工程.2016,23(10):1519-1522.Sun J Y, Zhang Y, Zhang J N, Zhao Z X. Prediction of Inclusion in Liquid Aluminum Based on BP Neural Network[J]. Control Engineering of China.2016,23(10):1519-1522.
[2]曾泉人,刘更,刘岚.机械加工零件表面完整性表征模型研究[J].中国机械工程,2010,21(24):2995-2999.Zeng Q R, Liu G, Liu L. Quantitative Description Model of Surface integrity for Machined Parts[J]. China Mechanical Engineering,2010,21(24):2995-2999.
[3]李力,王耀南,陈铁健.大尺寸LCD玻璃基板多视觉缺陷检测系统研究[J].控制工程.2016, 23(2):222-226.LI L, Wang Y N, Chen T J. Multi-visual Detect System for Large-size LCD Glass Substrate[J]. Control Engineering of China.2016, 23(10)1519-1522.
[4] E.S.Gadelmawla. A Vision System for Surface Roughness Characterization Using the Gray Level Co-occurrence Matrix[J]. NDT and E International, 2004, 7(7):577-588.
[5]张建.基于图像法的工件表面粗糙度检测系统研究[D].南京:南京航空航天大学,2011:10-30.Zhang J. Surface Roughness Measurement System Based on Image Method[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2011:10-30.
[6]郑秀艳.基于显微视觉的深孔微异型面粗糙度测量方法[D].大连:大连理工大学,2012:37-51.Zheng X Y. A Roughness Measurement Method Based on Micro-Vision for Micro-Heterogeneous Surface in Deep Hole[D].DaLian.Dalian University of Technology, 2012:37-51.)Haralick R M, Shanmugam K. Texture Features for Image Classification[J].IEEE Transactions on Systems, Man, and Cybernetics, 1973, 3(06):6102-6211.
[7]田欣利,王健全,张保国,等.基于纹理分析的Si3N4陶瓷表面粗糙度研究[J].材料工程,2012,12(9):7-13.Tian X L, Wang J Q, Zhang B Q. Surface rouughness of Si3N4 based on texture anlysis[J]. Journal of Materials Engineering. 2012,12(9):7-13.
[8]高程程,惠晓威.基于灰度共生矩阵的纹理特征提取[J].计算机系统应用,2010,19(6):195-198.Gao.C.C,, Hui X W. GLCM-based texture feature extration[J].Computer systems&Applications, 2010,19(6):195-198
[9]龚昌来,杨冬涛.一种改进的双线性插值图像放大算法[J].激光与红外,2009,39(8):899-901.Gong L L, Yang D T:Improved Image Zooming Algorithm Based on Bilinear Interpolation[J]. LASER&INFRARED.2009,39(8):899-901.
[10]张振杰,郝向阳,刘松林,程传奇.基于Hough一维变换的直线检测算法[J].光学学报,2016,36(4):1-8.Zhang Z J, Hao X Y, Liu S L, Cheng C Q.Line detction Based on Hough One-Dimensional Transform[J]. Acta Optica sinica,2016,36(4):1-8
[11] Duda R O, Hart P E. Use of the Hough transformation to detect lines and curves in pictures[J]. Communications of the Association for Computing Machinery, 1972,15(1):11-15.
[12] Chung Kuo-Liang, Huang Yong-Huai, Tsai Shiang-Ren.Orientation-based discrete Hough transform for line detection with low computational complexity[J]. Applied Mathematics and Computation, 2014,237:430-437.
[13]刘鳍洁,陈桂明,刘小方,等.BP神经网络权重和阈值初始化方法研究[J].西南师范大学学报(自然科学版).2010, 35(6):137-141.Liu Q J, Chen G M, Liu X F, et al.:Research on Initialization Algorithms of Weights and Biases of BP Neural Network[J]. Journal of Southwest China Normal University(Natural Science Edition).2010,35(6):137-141.
[14] Biswajeet Pradhan, Ahmed M. Youssef, Renuganth Varathrajoo.Approaches for Delineating Landslide Hazard Areas Using Different Training Sites in an Advanced Artificial Neural Network Model[J].Geo-Spatial Information Science,2010,02:93-102.
[15]孙金根,张颖,张嘉男,赵忠兴.基于BP神经网络的铝液夹杂物预测[J].控制工程.2016,23(10):1519-1522.Sun J Y, Zhang Y, Zhang J N, Zhao Z X. Prediction of Inclusion in Liquid Aluminum Based on BP Neural Network[J]. Control Engineering of China.2016,23(10):1519-1522.