期刊名称：Indian Journal of Computer Science and Engineering
印刷版ISSN：2231-3850
电子版ISSN：0976-5166
出版年度：2021
卷号：12
期号：6
页码：1559-1567
DOI：10.21817/indjcse/2021/v12i6/211206007
语种：English
出版社：Engg Journals Publications
摘要：Hyperspectral Images (HSI) provide a rich set of spatial and spectral information that is used for the classification of the HSI dataset. The large-scale hyperspectral image data leads to many processing challenges for the conventional data analysis techniques. To minimize the computational complexity and enhance the classification performance of the HSI dataset, we presented a new hybrid learning technique for feature extraction and classification (Hybrid-LN) model in this work. It is a simple two-step approach, to reduce computational complexity, the first step is applied to generate a spatial-spectral reduced HSI dataset by identifying the most significant pixels from each class and the most significant bands of the HSI. To increase HSI classification performance, the second step involves training a CNN to extract spatial-spectral features from the reduced HSI. Results from three benchmark HSI datasets - Salinas scene (SA), Indian Pines (IP), and Pavia University scene (PU)- are compared to those from the current models. Experimental results show that the computational complexity of the proposed approach is significantly reduced and producing relatively good classification accuracy with the state-of-the-art methods.
关键词：Hyperspectral Image;Spatial and spectral information;Classification;CNNs
