Comparative Study of ELM and SVM in Hyperspectral Image Supervision Classification

This work investigates the supervised classification of hyperspectral remote sensing images using Extreme Learning Machine (ELM) and Support Vector Machine (SVM) classifiers. The two methods are compared in terms of classification accuracy and computational efficiency. Experimental results show that SVM achieves slightly higher accuracy while ELM provides faster training speed, indicating complementary advantages for hyperspectral image classification tasks. Version information:This is the publisher's version (published PDF). The article was originally published in Remote Sensing Technology and Application on 20 February 2019. It is made available for self-archiving under the journal's CC BY-NC-ND 4.0 open access policy. 本文为正式出版排版版(出版社版本),依据《遥感技术与应用》期刊开放获取政策按 CC BY-NC-ND 4.0 协议自存档。