基于Tree Augmented Naive Bayes Classifier的影像纹理分类
Texture Classification Based on Tree Augmented Naive Bayes Classifier
-
摘要: 提出了一种松弛方法,允许类别节点下的相邻子节点之间存在相关关系(有向边),这种方法称为树增强型简单贝叶斯分类器(tree augmented naive Bayes classifier,TAN)。实验结果表明,TAN比简单贝叶斯分类器(naive Bayes classifier,NBC)可以获得更高的分类精度。Abstract: On the basis of the study of naive Bayes classifiers (NBC),a new method— tree augmented naive Bayes classifier is proposed and applied to texture classification.The experiment results demonstrate that the new method performs better in overall classification precision than NBC.
下载:
