Abstract
Segmentation of region of interest (ROI) is an important content in automated optic inspection (AOI). Aiming at the segmentation of ROI corresponding to various defects on the corrugated sheet of plate heat exchanger (PHE), a method based on discretization - recognition strategy is proposed. Corrugated sheet is a large complex curved surface. We find a way to regard it as a combination of several inclined planes and noncontiguous horizontal planes innovatively. Through using a typical AOI coaxial imaging system, the image marked by different gray values is obtained firstly. The inclined plane region is segmented according to the gray feature. Each horizontal plane region is discretized at the same time. Then, a method based on web crawler is proposed to recognize the specific category of each horizontal plane region. Finally, the surface of the corrugated sheet is divided into four types--inclined plane, high horizontal plane, middle horizontal plane and low horizontal plane. The experimental results demonstrate the great effect.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
