HSKL: A Machine Learning Framework for Hyperspectral Image Analysis
HSKL: A Machine Learning Framework for Hyperspectral Image Analysis
复制标题
DOI：
10.1109/whispers52202.2021.9483968
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Qian Cao;Deependra Mishra;John Wang;Steven T. Wang;Helena Hurbon;M. Berezin
中科院分区：
文献类型：
--
作者：
Qian Cao;Deependra Mishra;John Wang;Steven T. Wang;Helena Hurbon;M. Berezin
使用著名的scikit-learn软件包构建了一个新的基于高级机器学习的高光谱数据集分析框架HSKL。本文描述了HSKL的结构和基本用法。我们还通过应用17种分类算法展示了该软件包支持的模型的多样性，并测量了它们在分割具有高度相似光谱特性的对象时的基线性能。
A new framework for advanced machine learning-based analysis of hyperspectral datasets HSKL was built using the well-known package scikit-learn. In this paper, we describe HSKL’s structure and basic usage. We also showcase the diversity of models supported by the package by applying 17 classification algorithms and measure their baseline performance in segmenting objects with highly similar spectral properties.