Removing the Intensity Variations Caused by Textures on Textile Surfaces Using Wavelet Shrinkage
Hisanaga Fujiwara, Zhong Zhang · 2000
In this paper, we propose a new method for visual inspection of textile surfaces; selectively removing the intensity variations caused by textures on textile surfaces. For this purpose we use Wavelet Shrinkage, which was originally proposed by Donoho & Johnstone as a method to remove Gaussian white noise. We also propose a modification of Wavelet Shrinkage to selectively remove the intensity variations caused by textures as noise. Once the intensity variations caused by textures on textile surfaces are selectively removed, the remaining processings of inspection can be conducted in the image domain. So we can utilize the image processing methods and techniques developed so far for the visual inspection of other industrial products. 1