基于数学形态学的肝脏B超图像的纹理识别
摘 要
基于数学形态学的理论,分析了肝脏B超图象的纹理特征,提出了一种纹理特征抽取算法,它具有旋转不变性,通过分类实验与已有的基于数学形态学的特征进行了比较,实验结果表明提出的方法分类精度高,计算理小。
关键词
Texture Recognition of B-Scan Ultrasonic Images of Liver Based on Mathematical Morphology
() Abstract
Based on mathematical morphology, this paper analyses texture feature of B-scan ultrasonic images of liver and presents an algorithm for rotation invariant texture feature extraction. Compared with other morphology-based algorithms, experimental results show that our texture feature has high classification accuracy.
Keywords
|