Binarization Using Morphological Decomposition Followed by cGAN

Abstract

This paper presents a novel binarization scheme for stained decipherable patterns. First, the input image is downsized, which not only saves the computation time, but the key features necessary for the successful decoding is preserved. Then, high or low contrast areas are decomposed by applying morphological operators to the downsized gray image, and subtracting the two resulting output images from each other. If necessary, these areas are further subjected to decomposition to obtain finer separation of regions. After the preprocessing, the binarization can be done either by GMM to estimate a binarization threshold for each region, or the binarization problem is treated as an image-translation task and hence the conditional generative adversarial network (cGAN) is trained using the high or low contrast areas as conditional inputs.