Paper Defect Detection Algorithm Based on the Mathematical Morphology and Computer Vision

Abstract A method for detecting paper’s surface defects is proposed, which based on mathematical morphology algorithm and computer vision technique. Firstly, the mean filtering wavelet denoising in image pre-processing are used to eliminate noise, analysis can achieve enhancement increase contrast between target area background. And then, an improved threshold Canny operator segment extract complete scratch line other defect edges. Finally, region features coloured by processing. The method’s stimulating result verified Matlab software, from we conclude that effect very effective.