Image Segmentation of Printed Fabrics with Hierarchical Improved Markov Random Field in the Wavelet Domain

An improved MRF algorithm-hierarchical Gauss Markov Random Field model in the wavelet domain is presented for fabric image segmentation in this paper, which obtains the relation of interscale dependency from the feature field modeling and label field modeling. The GaussMarkov random field modeling is usually adopted to feature field modeling. The label field modeling employs the interscale causal MRF model and the intrascale noncausal MRF model. After that, parameter estimation is the essential section in the interscale, enhancing modeling capabilities of the pixels partial dependency. Sequential maximum a posterior criterion is applied to achieve the results of image segmentation. Comparisons with other hybrid schemes, results are indicated that performance of the presented algorithm is effective and accurate, in terms of classification accuracy and kappa coefficient, for patterned fabric images.