Detecting fabric defects with computer vision and fuzzy rule generation Part I: Defect classification by image processing

A fabric defect detecting system that uses an advanced method involving com puter vision and image analysis is capable of defect classification. Image pre-processing techniques that enhance raw images are applied before defect classification by a K-means algorithm and statistical method. These genera te a Bayes classifier from which a decision surface is created for a classi fication procedure that can categorize defective or nondefective regions. D efect detection of the test fabric image is implemented by the decision sur face from the training fabric image. The advantages of using the decision s urface are a reduction in the training step and the ability to rapidly clas sify fabric. Experimental results confirm the reliable and reasonable class ification ability of the proposed system.