Abstract
Continuously rotating eggs were inspected for cracks by a PC-based computer vision system. A sequence of three images per egg were sufficient to identify over 90% of eggs with cracks. The diameter of each egg measured in software was used to control the image acquisition process. Response surface analysis showed that inspection success rate was dependent on egg size and two software calibration constants.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have