GREY LEVEL THRESHOLDING IN BADLY ILLUMINATED IMAGES

Abstract

Most grey level thresholding methods produce very good results in situations where the illumination gradient in the original raster image is regular and not too large. In other cases, such as a large linear change in illumination, a satisfactory bi-level image cannot be produced. One approach is to locate object pixels first, and then grow regions around these, generating a threshold value for each pixel.