A VISION SYSTEM FOR ONLINE WEAR DETECTION
Abstract
Wear detection has traditionally restricted itself to offline study and measurement. In this paper a vision system for online monitoring and detection of wear is described. This system uses a video zoom microscope and a high-resolution monochrome camera to capture the image series of a moving surface under study. An algorithm based on multichannel filtering for the detection of wear patterns is presented. The wear patterns are extracted by filtering the acquired image using a Gabor filter bank with multiple narrow spatial frequency and orientation channels. Experiments show the feasibility and usefulness of the proposed vision system and detection method of wear patterns.
Event details
- Event
- XVII IMEKO World Congress
- Place
- Dubrovnik, CROATIA
- Time
- 22 June 2003 - 28 June 2003
- Website
- http://www.hmd.hr/imeko/