Texture image segmentation based on wavelet-domain hidden Markov models

Many approaches have been used to segment texture-based image, but can´t have one´s wish fulfilled. People unremittingly try to find high quality, more effective method. The 2D discrete wavelet transform, as a powerful and effective approach, have got preferable production in image analyzing and image processing. However routine method focuses on the assumption that the wavelet coefficients are independent and jointly Gaussian. In fact, most real-world images are not always Gaussian distributed, there are underlying relationships and rules among these wavelet coefficients on both the same scale and the inter-scale. In this paper, we first reveal the dependencies among these coefficients through the wavelet-domain HMM´s, then estimate the model parameters using the expectation maximization (EM) algorithms. The classification can be first realized through maximum likely method in each band, and then combine with the classification results of the three sub-bands from the 2D wavelet transform and also integrate the classification results of different scale. These approaches offer improved segmentation accuracy