IEEE

Spectral Structure-Aware Initialization and Probability-Consistent Self-Training for Cross-Scene Hyperspectral Image Classification

Abstract: Cross-scene classification of hyperspectral images (HSIs) aims to classify target domain (TD) data using only labeled source domain (SD) data and unlabeled TD data during training. However, ...
IEEE

Research on Hyperspectral Image Classification Based on IF-ICA and Multi-Kernel SVM

Abstract: Applying Support Vector Machine (SVM) theory to hyperspectral images classification can significantly mitigate the decline in classification performance caused by the curse of dimensionality ...