An Adaptive Background Adjusting Algorithm for Rail Surface Defect Image Segmentation

Aiming at the problem of false segmentation caused by the change of illumination and properties of surface reflection when extracting rail surface defects, this paper proposes an adaptive background adjusting algorithm for rail surface defect image segmentation based on the background subtraction method. Firstly, a new similarity measure is proposed by combining Coefficient of Variation (CV) of the pixel gray level with the non-local normalization factor in the image. Secondly, by adjusting the size of window for neighborhood averaging adaptively according to the similarity measurement results, the background image model is established. Finally, the image subtraction operation is made and the segmentation of rail surface defect is realized by setting up dynamic threshold value for the differential image. The experimental results show that this method has a good effect on segmentation of both block and linear defects distributed discretely in the image.