Abstract
Automated inspection of apples requires that the entire surface of the fruit passes through the view of at least one camera. This work uses Monte Carlo simulation to investigate the extent of coverage of the apple surface when viewed by three four and five cameras arranged in a plane. Each camera has a circular inspection area that is 45 to 50% of the apple size. The number of images per apple rotation and the level of asymmetry (or drunkenness) of the apple's roll are varied to determine their effect on the extent of surface coverage. Results for a single rotation of the apple show that complete surface coverage is not possible with three cameras and up to 30 images per rotation. Four cameras can provide complete surface coverage at 30 images per rotation and five cameras can provide complete surface coverage at 15 images per rotation. The greater the extent of surface coverage the greater the redundancy in inspection and the greater the possibility of false positives. However it is likely that several inspections of each defect will provide more secure recognition than that provided by just one sight of the defect. Increase in the drunkenness of the apple roll has a large adverse effect on the extent of surface coverage and redundancy.
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.
