Texture image segmenting method based on reinforced airspace-transform domain statistical model

Abstract

The invention discloses a texture image segmenting method based on a reinforced airspace-transform domain statistical model, belonging to the technical field of image processing and mainly solving the problems of poor segmenting accuracy and high calculating complexity in the prior texture image segmenting method. The method comprises the following segmenting steps: (1) inputting a texture image and the texture category number; (2) dividing the texture image into thick image blocks with the length and the width of 16 and carrying out two-dimensional discrete wavelet transform on each image block; (3) training an EHMM-HMT parameter and calculating a likelihood value and a segmenting result in a thick scale of the thick image block; (4) dividing the texture image into thin image blocks with the lengths and the widths of respectively 8, 4 and 2; (5) calculating a likelihood value and a segmenting result in each thin scale of the thick image block; and (6) combining the multiple dimensioned MAP fusion of boundary information. The invention has the advantages of high segmenting accuracy and low calculating complexity of the texture image and can be used for segmenting a microtexture image and a macrotexture image.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for segmenting texture images, which can be used for segmenting SAR images. Background technique [0002] For a long time, scholars at home and abroad have proposed a large number of texture image segmentation methods, mainly including co-occurrence matrix method, method based on wavelet and Gabor filter, Markov random field method and so on. In recent years, multi-scale ideas have been widely used in the field of image segmentation. The advantage of multi-scale decomposition of images is that low-resolution images greatly reduce the complexity of image processing, and at the same time provide guidance for the processing of high-resolution images. Information, thereby greatly reducing the dependence of image processing on prior knowledge. From the perspective of processed image features, multi-scale segmentation methods can be divided into two categories based o...

AI Technical Summary

Problems solved by technology

However, when using the HMM-HMT model to calculate the initial segmentation on each scale, it is necessary to train the parameters of the HMM-HMT model on each scale separately, thus greatly increasing the computational complexity; if in order to reduce the computational complexity, only the most The initial segmentation on the coarse scale does not calculate the HMM-HMT model parameters on the other fine scales, which will cause the defects of poor regional consistency and poor boundary preservation of the final segmentation results.

Images