Extraction Method for the Surface Image Defects of the Magnetic Tile Based on Adaptive Gaussian Filtering

Abstract

This paper proposed a defects extraction method based on one-dimensional adaptive Gaussian filtering. To overcome the difficulties as various defects, low contrast, complex background and overall uneven brightness, this method designed a new one-dimensional adaptive Gaussian filter based on the defect size. According to the gray change of the magnetic tiles surface image in the different regions, we progressed the Gaussian filtering based on the selective one-dimensional scan line by region, and made the width of the filter can automatically adjust with the defect size, simulated the threshold value curve, and extracted the magnetic tiles surface defects. The experiment shows that this method can accurately and quickly extract the various types of defects of the magnetic tile surface.