CORK QUALITY CLASSIFICATION-SYSTEM USING A UNIFIED IMAGE-PROCESSING AND FUZZY-NEURAL NETWORK METHODOLOGY

Cork is a natural material produced in the Mediterranean countries. Co rk stoppers are used to seal wine bottles. Cork stopper quality classi fication is a practical pattern classification problem. The cork stopp ers are grouped into eight classes according to the degree of defects on the cork surface. These defects appear in the form of random-shaped holes, cracks, and others. As a result, the classification cork stopp er is not a simple object recognition problem. This is because the pat tern features are not specifically defined to a particular shape or si ze. Thus, a complex classification form is involved. Furthermore, ther e is a need to build a standard quality control system in order to red uce the classification problems in the cork stopper industry. The solu tion requires factory automation meeting low time and reduced cost req uirements. This paper describes a cork stopper quality classification system using morphological filtering and contour extraction acid follo wing (CEF) as the feature extraction method, and a fuzzy-neural networ k as a classifier. This approach will be used on a daily basis. A new adaptive image thresholding method using iterative and localized schem e is also proposed A fully functioning prototype of the system has bee n built and successfully tested. The test results showed a 6.7% reject ion ratio. It is compared with the 40% counterpart provided by traditi onal systems. The human experts in the cork stopper industry rated thi s proposed classification approach as excellent.