Global Interpretation and Local Analysis to Measure Gears Eccentricity
This paper presents a data-driven approach to profile fitting where global constraints are imposed to local measurements. The local measurements are obtained from partial analysis of the objects under consideration. Prior knowledge of the object under analysis provides global constraints. To illustrate these concepts, it is developed the exercise of measuring a gear’s boundary from its teeth profile. A framework is developed to extract local parameters from frame to frame and to enforce morphologic constraints over the whole sequence. It is shown how a combination of accurate local processing techniques and global knowledge can solve the tradeoff between what can be perceived locally and interpreted globally.
Unable to display preview. Download preview PDF.
- 1.Marr, D.: Vision. W.H. Freeman, New York (1982)Google Scholar
- 2.Ullman, S.: High-Level Vision. MIT Press, Cambridge (1995)Google Scholar
- 3.Wilson, B.A.: Dimensioning and Tolerancing Handbook. Genium Publishing (1995)Google Scholar
- 7.Maintz, Viergever: A Survey of Medical Image Registration. Medical Image Analysis 2(1) (1998)Google Scholar
- 9.Shi, J., Tomasi, C.: Good Features to Track. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 593–600 (1994)Google Scholar
- 13.Press, W.H., Vetterling, W.T., Teukolsky, S.A., Flannery, B.P.: Numerical Recipes in C++: the Art of Scientific Computing. Cambridge University Press, Cambridge (2002)Google Scholar