MRF Regularization Models For Adaptive Binarization Of Non-Uniform Images

In this paper, we present two connected MRF models, the edge-preserving smoothing model followed by the modified standard regularization, for the adaptive binarization of the non-uniform images in the presence of noise. In particular, we have developed the computational model for the modified standard regularization method to be used to calculate the adaptive threshold surface for noisy images. Since the modified standard regularization depends only on image data, and not its edge segments, it gives much better performance and can be applied to more classes of images than those methods which rely on edge segments. Experimental results demonstrate that the proposed method has the best performance over three other commonly used adaptive segmentation methods, and it is faster than previous interpolation-based thresholding techniques. Indexing terms: adaptive image binarization, threshold surface, MRF models, edge-preserving smoothing, standard regularization