期刊文献+

基于机器视觉的圆环形零件形位尺寸自动测量 被引量:12

Measurement of Circular Ring Parts' Form and Position Size Base on Machine Vision
下载PDF
导出
摘要 采用机器视觉技术实现对圆环形零件内外径和同心度的非接触式测量。使用200万像素USB数字摄像机获得零件图像,对图像采用双峰法寻找到合适的阈值将图像二值化,运用轮廓跟踪法找到零件的边缘,对边缘数据采用最小二乘法拟合求出零件的内外径和同心度。对1~2cm外径的零件进行实验,绝对误差小于一个像素,与人工测量值对比,最大误差不超过0.03mm。研究结果表明:在机器视觉测量中,摄像机的像素越大、被测物体尺寸越小,则测量精度越高,所以采用高分辨率的摄像机可以实现对高精度的微小零件测量。 In this paper,technology of machine vision is used to measure circular ring parts' inside and outside diameter and concentricity.The picture of parts is got by 2 million-pixel USB digital camera.During processing,firstly,using bimodal method to find appropriate threshold to get binary image.Secondly,using contour-tracing method to find edge of the parts;thirdly,us- ing the edge data to get the parts' inside and outside diameter and concentricity through least-squares method.Experiment of 1~2cm diameter parts,absolute error is less than one pixel.The largest error is less than 0.03mm compared with the manual measurements.The results show that:In the machine vision measurement,the higher the camera's pixel level is and the smaller size of the measured object is,the higher the measurement's accuracy.So high level pixel camera can be used to measure high-precision small parts.
出处 《工业控制计算机》 2010年第7期1-3,共3页 Industrial Control Computer
关键词 零件测量 机器视觉 数字图像处理 最小二乘法 parts measurement machine vision digital image process least-squares method
  • 相关文献

参考文献6

二级参考文献31

  • 1于忠党,王龙山,陈向伟.基于支持向量回归的零件直线边缘亚像素图像检测[J].吉林大学学报(工学版),2006,36(3):371-375. 被引量:5
  • 2Burge C J C. A tutorial on support vector machines for pattern recognition[J ]. Data Mining and Knowledge Discovery, 1998, 2(2) : 121- 167.
  • 3Vapnik, V. An overview of statistical learning theory[J]. IEEE Neural Networks, 1999, 10(5):988-999.
  • 4Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9(3) : 293- 300.
  • 5Suykens J A K, Vandewalle J, De Moor B. Optimal control by least squares support vector machines[J]. Neural Networks, 2001, 14(1): 105-113.
  • 6Peng Daiqiang, Liu Jian, Tian Jinwen, et al. Transformation model estimation of image registration via least square support vector machines[J]. Pattern Recognition Letters, 2006, 27(12):1 397-1 404.
  • 7Gao J B, Harris C J, Gunn S R. On a class of support vector kernels based on frames in function Hilbert spaces[J]. Neural Computation, 2001, 13(9) : 1 975-1 994.
  • 8[1]Pal N R,Pal S K.A Review on Image Segmentation Techniques[J].Pattern Recognition,1993,26(9):1277-1294.
  • 9[2]Bhanu B,Lee S,Ming J.Alaptive Image Segmentation Using a Genetic Algorithm[J].IEEE Trans.on System,Man,and Cybernetics,1995,5(12):1543-1565.
  • 10[3]Doyle W.Operation Useful for Similarity-Invariant Pattern Recognition[J].J.Asssoc.Comput.Mach.,1962,9:259-267.

共引文献358

同被引文献114

引证文献12

二级引证文献73

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部