Design and development of a vision based leather trimming machine

The objective of the work described in this paper is to demonstrate a laboratory prototype for trimming the external part of a hide, assuming that the resulting machine would eventually form part of a completely automatic system in which hides are uploaded, inspected and parts for assembly are downloaded without manual intervention and prior sorting. Detailed literature and international standards are included. The expected advantages of integrating all vision based functions in a single machine, whose basic architecture is proposed in the paper, are also discussed. The developed system is based on a monochrome camera following the leather contour. This work focuses on the image processing algorithms for defect detection on leather and the NC programming issues related to the path following optimization, which have been successfully tested with different leather types.