B超图像纹理的复杂性分析

Analysing the complexity of the textures of ultrasonic images

本文提出一种复杂性度量法对肝脏Ｂ超图像纹理的分类进行了研究，图像的灰度值复杂性作为纹理特征。通过改变复杂性的计算方法得到两个方向的特征值为特征向量，用贝叶斯分类器分类对图像纹理分类。实验结果表明该方法有效。

This paper presents a method for analyzing the ultrasonic liver images textures. The texture signature is taken to be a complexity of image gray levels. We change the method of complexity measures and compute this signature in two orientations, then get an attribute vector. The experimental results of texture classification by using Bayesian classifier show the method is efficient.