针对复杂背景中目标边缘提取的问题,提出一种基于梯度幅度直方图和类内方差进行边缘提取的新方法———CAGH(cluster algorithm based on gradient histogram)算法。该算法先分析经“非最大梯度抑制”后的梯度幅度直方图的特征,确定边缘集中区域,再通过类内方差确定梯度阈值,并利用该阈值确定边缘。在车牌识别中运用该方法提取复杂背景中的车牌边缘,并与Sobel、Canny等算法进行了比较。结果表明,CAGH算法适应性强、提取效率高,提取的是连通性、独立性好的单像素边缘,有利于后续的特征提取和模式识别。
Bayesian network has a powerful ability for reasoning and semantic representation, which combined with qualitative analysis and quantitative analysis, with prior knowledge and observed data, and provides an effective way to deal with prediction, classification and clustering. Firstly, this paper presented an overview of Bayesian network and its characteristics, and discussed how to learn a Bayesian network structure from given data, and then constructed a Bayesian network model for land resource evaluation with expert knowledge and the dataset. The experimental results based on the test dataset are that evaluation accuracy is 87.5% , and Kappa index is 0.826. All these prove the method is feasible and efficient, and indicate that Bayesian network is a promising approach for land resource evaluation.
