遥感影像的全模糊监督分类
A Fully Fuzzy Supervised Classification of Remotely Sensed Imagery
-
摘要: 设计了一个基于神经元网络的全模糊训练、分类和精度评估方法,并成功地应用于一个城郊型土地覆盖分类。结果表明,该方法灵活、适应性强,并能取得较好的分类精度。Abstract: This paper presents a fully fuzzy strategy for image classification based on a neural network architecture, which promises to overcome some problems encounered in a conventional crisp even fuzzy classification process. The proposed method was successfully applied in a classification of a suburban land cover with resuls confirming the flexibility and practicality of this fully fuzzy approach.