A machine vision system for classifying rectangular cabinet frames

Abstract

This thesis describes a machine vision solution to an industrial classification task. The specific problem is the identification of kitchen cabinet frames that travel on a conveyor belt. For these components, it is possible to acquire silhouette images and perform two dimensional image analysis. Corner point locations are used as features which are compared with a database of known frame styles. This thesis describes a novel image acquisition system that utilizes backlighting and a line scan camera. Several corner detection methods are compared and a mathematical formulation of frame comparison is given. A fast database search technique is also presented. The laboratory system has been successfully tested with a set of 27 cabinet frames.