多分类SVM主动学习及其在遥感图像分类中的应用

针对应用传统分类器和被动学习的方法,难以满足遥感图像处理实际应用的要求这一困境,提出了一种新的基于多分类SVM的主动学习方法,与被动学习的随机选择不同,主动学习是在少量标记类别的初始训练样本集基础上,通过反复迭代主动学习的方式,得到最有利SVM分类器性能的样本为支持向量。研究表明,这种方法直接避免了大量的计算,可有效地减少样本训练时需要标记样本的数目,并取得较为理想的分类效果。

Remote sensing lmage classification using active learning with multiclass support vector machine

More and more difficulties are encountered when using traditional classifier and passive learning to classify remote sensing image.In order to overcome these crucial issues,a new classification framework about remote sensing image classification method using active learning with multiclass support vector machine was addressed.Instead of using a randomly selected training set,it was initially designed using a small set of labeled points,and subsequently refined by actively querying for the labels of pixels f...