Title: A Novel Graph Based Label Propagation Method for Hyperspectral Remote Sensing Data Classification
Abstract: For hyperspectral image classification, we present a novel graph based semi-supervised classification method that learns from similarity and dissimilarity on labeled and unlabeled data, which contain both the adjacency graph and the dissimilar graph. Since manifold learning approach is capable of exploring the manifold geometry of data, it is suitable for calculating the adjacency graph with label similarity. A manifold learning method was utilized to calculate the adjacency graph. Dissimilarity among examples probably be used to construct the dissimilar graph, which is hard to grasp. The dissimilar probability was proposed to construct the dissimilar graph, which has effectively improved the classification accuracy of hyperspectral data in experiment.
Publication Year: 2018
Publication Date: 2018-07-01
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
Cited By Count: 2
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot