A neurofuzzy color image segmentation method for wood surface defect detection

In the last decades, several automated visual inspection (AVI) systems have been developed and applied to a wide range of products, including wood (Pham and Alcock 2003). AVI is an automated form of quality control normally achieved using a camera connected to a computer. The AVI framework includes five processing stages: image acquisition, image enhancement, image segmentation, feature extraction, and classification. A review of AVI research applied to the inspection of wood boards concluded that segmentation is often the most timeconsuming part of the process, and that it usually does not locate all defects properly. It is necessary to develop new segmentation algorithms that can separate all defects from clear wood in the image (Pham and Alcock 1998).