为提取云团反射率图像内部层次类特征和轮廓线上不规则的凹陷类特征,在构建基于图像内容的层次结构模型的基础上,提出相对极坐标系下的距离链码和基于八方向链码的累积导数和差码方法,前者用于层次类特征提取,后者用于轮廓形态特征的提取,构建梯度特征、云砧特征以及凹陷特征的提取算法.实验证明,该方法下的特征类间区分度高,运行速度快,可用于解决非刚体图像的相关特征的提取.%In this paper, a new method was proposed on the basis of hierarchical structure model of image content. Distance chain code was put forward under relative polar coordinate system, as well as difference value code derived from the sum of accumulation of derivatives based on 8-direction chain code. Distance chain code was applied to extract internal structure category features, and the difference value code was used to extract the contour morphological characteristics. Then the algorithm extracting gradient, cloud anvil and concave of contour features was designed. The experimental results show that the extracted features have high separability between classes and the processing speed is fast. This method can be used to extract the features of non-rigid images.
展开▼
