Feature selection is one of the most important problems in hyperspectral images classification. It consists to choose the most informative bands from the entire set of input datasets and discard the noisy, redundant and irrelevant ones. In this context, we propose a new wrapper method based on normalized mutual information (NMI) and error probability (PE) using support vector machine (SVM) to reduce the dimensionality of the used hyperspectral images and increase the classification efficiency. The experiments have been performed on two challenging hyperspectral benchmarks datasets captured by the NASA's Airborne Visible/Infrared Imaging Spectrometer Sensor (AVIRIS). Several metrics had been calculated to evaluate the performance of the proposed algorithm. The obtained results prove that our method can increase the classification performance and provide an accurate thematic map in comparison with other reproduced algorithms. This method may be improved for more classification efficiency. Keywords-Feature selection, hyperspectral images, classification, wrapper, normalized mutual information, support vector machine.
翻译:选择特征是超光谱图像分类中最重要的问题之一,它包括从整个一组输入数据集中选择信息最丰富的频带,并抛弃噪音、冗余和不相干的数据。在这方面,我们提议基于标准化的相互信息(NMI)和误差概率(PE)的新包装方法,使用支持矢量机(SVM)来降低所使用的超光谱图像的维度,提高分类效率。对美国航天局空载可视/红外成像光谱传感器(AVIRIS)所捕捉的两个具有挑战性的超光谱基准数据集进行了实验。为评估拟议算法的性能计算了若干尺度。获得的结果证明,我们的方法可以提高分类性能,并与其他复制的算法相比,提供准确的专题地图。为了提高分类效率,可以改进这一方法。关键词-地形选择、超光谱图像、分类、包装、普通的相互信息、支持矢量机。