Texture image segmentation method based on independent Gaussian hybrid model

Abstract

The invention discloses a texture image segmentation method based on an independent Gaussian hybrid model, which comprises the following segmentation steps: simultaneously performing three-layer wavelet transformation, dual-tree complex wavelet transformation and Contourlet transformation to training texture images; extracting the characteristics of the corresponding training texture images; selecting the characteristics by adopting an immunity clone algorithm on each layer; performing unsupervised learning of the Gaussian hybrid model to each layer of each training image, adaptively obtaining the corresponding component number, and thus obtaining the parameter of the Gaussian hybrid model; simultaneously performing wavelet transformation, dual-tree complex wavelet transformation and Contourlet transformation to test texture images; calculating the corresponding final likelihood value of each layer according to the transformation coefficient and the component number; obtaining the primary segmentation result through comparing the corresponding likelihood value of each texture; and obtaining the segmentation result through multi-scale fusion of the primary segmentation result. The invention has the characteristics of good consistence of segmentation area, complete information retaining, and accurate edge positioning, and can be used for the image texture recognition.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to a texture image segmentation method, which can be used for image understanding and recognition. Background technique [0002] Texture image analysis and segmentation is one of the most classic research topics in image processing and computer vision. It plays an important role in national defense and national economy. It is used in image classification, image retrieval, image understanding, target recognition and other issues. played a key role. The purpose of texture segmentation is to divide an image into uniform regions and to determine the boundaries between regions. The regional consistency in the texture image is represented by the consistency of certain features of the texture in the region, and the segmentation must be performed on one or some features. Therefore, the extraction of texture features is a crucial factor affecting texture image segmentation. [0003] The curr...

AI Technical Summary

Problems solved by technology

However, this type of method is sensitive to initialization due to the use of EM algorithm to train the model, which makes the robustness of the segmentation results poor.

Images