Landcover classification with self-taught learning on archetypal dictionaries
Landcover classification with self-taught learning on archetypal dictionaries
复制标题
DOI：
10.1109/igarss.2015.7326282
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
R. Roscher;Christoph Römer;B. Waske;L. Plümer
中科院分区：
文献类型：
--
作者：
R. Roscher;Christoph Römer;B. Waske;L. Plümer
本文介绍了原型字典的自学框架的土地覆盖分类的应用。自学学习，一种无监督的表示学习方法，被用来学习低维和判别性的高级特征，这些特征被用作分类算法的输入。实验进行了使用多光谱Landsat 5 TM图像的一个研究区在北部的Novo Progresso位于南美洲。我们的研究结果证实，自学与原型字典提供的功能，可以作为输入到线性逻辑回归分类。所获得的分类精度与使用原始特征的基于核的分类器相当。
This paper introduces archetypal dictionaries for a self-taught learning framework for the application of landcover classification. Self-taught learning, an unsupervised representation learning method, is exploited to learn low-dimensional and discriminative higher-level features, which are used as input into a classification algorithm. Experiments are conducted using a multi-spectral Landsat 5 TM image of a study area in the north of Novo Progresso located in South America. Our results confirm that self-taught learning with archetypal dictionaries provide features, which can be used as input into a linear logistic regression classifier. The obtained classification accuracies are comparable to kernel-based classifier using the original features.