Web Surface Defect Segmentation Based on Stationary Wavelet Transform

Abstract

Typical characteristics of web manufacturing process ,when compared with other sheet or flat product manufacturing, are the large value of web width and production speed .So the development of new and efficient algorithm invokes the interests of many researchers. This paper describes a novel approach based on stationary wavelet transform for the segmentation of web surface defect. The segmentation is performed firstly by decomposing the gray level image into sub-band images and then by an image fusion scheme for the sub-images. Compared with orthogonal wavelet transform (OWT), the notable advantage of stationary wavelet transform (SWT) is its shift invariance. These properties are especially important for defect detection. Image fusion makes full use of available information in each sub-band images to obtain better output results when compared with ordinary image enhancement. Experimental results demonstrate the validity of our method. The proposed method is targeted for web surface defect inspection but has the potential for broader application areas such as steel, wood and fabric defect detection. With the development of high performance signal processors, spectral analysis or a combination of statistical and spectral analysis would be the trend of web surface defect inspection.