Detection of Crassostrea virginica hinge lines with machine vision: software development

Abstract

Shucking (removing the meat from the shell) an oyster requires that the muscle detachments to the two shell valves and the hinge be severed. Described here is the computer vision software needed to locate the oyster hinge line so it can be automatically severed, one step in the development of an automated oyster shucker. Oysters are first prepared by washing and trimming off a small shell piece on the oyster hinge end to provide access to the outer hinge surface. A computer vision system employing a color video camera then grabs an image of the hinge end of the oyster shell. This image is processed by the computer using software. The software is a combination of commercially available and custom written routines that locate the oyster hinge. The software uses four feature variables, circularity, rectangularity, aspect-ratio, and Euclidian distance, to distinguish the hinge object from other dark colored objects on the hinge end of the oyster. Several techniques, including shrink–expand, thresholding, and others, were used to secure an image that could be reliably and efficiently processed to locate the oyster hinge line.