Abstract
Nowadays, intelligent robot technology is extensively used in every aspect of human existence and production. To achieve automatic sorting, future development must concentrate on employing intelligent robots instead of humans. Coin sorting robots are an important research object in the field of sorting robots. This paper focuses on a machine vision (MV) sorting especially difficult application, in which the `part' is an Indian coin. The lack of distinguishing characteristics between denominations and the variation in features within a single denomination makes the application difficult in part. Even though coin recognition algorithms have been published in the literature, most applications are evaluated offline using the coins' weights. In the end, it was determined that none of these three methods achieved the desired 95% accuracy at 1000 coins per minute.
Sign-in/Register to access full text options 
Free) 
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 call
