ARTIFICIAL-INTELLIGENCE BASED TECHNIQUES FOR PROCESSING SEGMENTED IMAGES OF WOOD BOARDS

Veneer boards are made by bonding together thin sheets of wood. Normal ly, grading of these sheets is carried out to ensure that only high-qu ality sheets are used to make high-quality boards. Frequently, this qu ality control task is performed by a human inspector. However, due to the speed and repetitive nature of the job, human graders cannot alway s grade the boards accurately. To improve the efficiency of grading, a ttempts are being made to automate it using automated visual inspectio n (AVI). Integral to the AVI process is segmentation, which is concern ed with separating clear wood and defective areas in the image. The de fective areas are labelled as segmented objects. However, after segmen tation has been performed, two problems can occur. Firstly, clear wood areas may be falsely detected as defects and, secondly, a defect may be represented by more than one segmented object. This paper describes two techniques that have been used to overcome these problems. The te chniques were inspired by the artificial intelligence (AI) techniques of fuzzy logic and self-organizing neural networks.