Surface defects classification using artificial neural networks in vision based polishing robot
ICIRA'11 Proceedings of the 4th international conference on Intelligent Robotics and Applications - Volume Part II
Wavelet-based defect detection in solar wafer images with inhomogeneous texture
Pattern Recognition
| Hi-index | 0.02 |
Automatic surface defect detection with vision systems can bring manufacturers a number of significant benefits, especially when used on-line. This non-contact method may present an alternative to allow the surface defect to be measured rapidly and with an acceptable accuracy. One of the most promising of the non-contact methods in terms of speed and accuracy is the computer vision technique. This paper basically defines a surface defect characterization using contour dispersion. The basic idea of this research is to find an optimal gray-level threshold value for separating objects of interest in an image from the background based on their gray-level distribution using contour dispersion level to find the characteristic of surface defect. Next, the research direction has been suggested to develop an automatic polishing robot system using vision sensor based on surface defect characterization.