Many smooth, highly specular coatings, such as automotive paints, are subjected to considerable performance demands and manufacturers spend significant sums each year to monitor and repair coating surface quality. Additionally, changing product specifications and environmental regulations will continue to affect the processing parameters that influence surface appearance and quality. Therefore, it is vital to develop robust methods to monitor surface quality on-line and continuously examine the processes that significantly affect surface appearance in real time. As a critical first step, this paper presents a machine vision system design that utilizes surface reflectance models as a rational basis. Experimental and numerical investigations of specular and diffuse images of a range of specular coated surfaces confirm that these images efficiently yield information that corresponds strongly to human assessment and ranking.
|Number of pages||8|
|Journal||Proceedings-IEEE International Conference on Robotics and Automation|
|State||Published - 2002|
ASJC Scopus subject areas
- Control and Systems Engineering
- Artificial Intelligence
- Electrical and Electronic Engineering