Defect detection of particleboards by visual analysis and machine learning

Abstract

Particleboards may exhibit several defect types caused by a variety of sources during the manufacturing process. It is essential to quickly determine when a defect is present and localize the fault so that the board can either be fixed or discarded. Several methods have been already been developed to address this issue to varying degrees of success. In this work, a novel process is presented which quickly determines whether a defect exists or not using traditional machine learning techniques on a bivariate color histogram of the particleboard and then localize the defect using automated image manipulation techniques. The workflow of quickly determining if a defect is present then using a more computationally intensive technique to localize and classify the defect can be extended to use other methods or even to other processes.