介绍了Bayesian线性规划的基本原理,利用它解决带有不确定性MRF(尔柯夫随机场)参数的影像纹理识别问题,并提出了将不确定性状态参数变成确定性参数的5种选择方法。通过使用实际航空影像的对比识别实验,给出一个合理的选择方法。本方法为解决纹理识别中带有不确定性特征参数的处理提供了新的途径。
A new method based on Bayesian linear programming is proposed for texture recognition of aerial image with uncertainty MRF parameters. The basic principle and the main idea of this method are introduced, and five different methods are provided to be selected, which transform MRF parameters from uncertainty to certainty. The experiments show that this proposed method is reasonable and promising in the future.