Title | ||
---|---|---|
Mutual-Information-Based Semi-Supervised Hyperspectral Band Selection With High Discrimination, High Information, and Low Redundancy |
Abstract | ||
---|---|---|
The large number of spectral bands in hyperspectral images provides abundant information to distinguish different land covers. However, these spectral bands have much redundancy and bring an extra computational burden. Thus, band selection is important for hyperspectral images. Since the labeled samples are difficult to obtain, a semi-supervised criterion based on maximum discrimination and information (MDI) is defined by using both limited labeled samples and sufficient unlabeled samples. This MDI criterion aims to select the most highly discriminative and informative bands, but it is hard to accurately calculate. Therefore, a novel criterion based on high discrimination, high information, and low redundancy (DIR) is proposed as its low-order approximation. Moreover, from an information theory perspective, a theoretical proof is given that many traditional semi-supervised feature selection criteria are the low-order approximations of this MDI criterion. Compared with them, the proposed criterion needs more relaxed approximation conditions. To search and optimize the proposed criterion, a novel clonal selection algorithm is proposed, where the adaptive clone and mutation operators are devised to speed up the convergence. Experimental results on hyperspectral images demonstrate the effectiveness of the proposed semi-supervised band selection method. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/TGRS.2014.2367022 | IEEE T. Geoscience and Remote Sensing |
Keywords | Field | DocType |
mutation operators,spectral band,low-order approximation,land cover,semisupervised learning,limited labeled sample,approximation theory,learning (artificial intelligence),hyperspectral band selection,clonal selection algorithm (csa),semi-supervised learning,clonal selection algorithm,unlabeled samples,dir,convergence,information theory,maximum discrimination and information,mutual information-based semisupervised hyperspectral band selection,mdi criterion,semi-supervised feature selection criteria,geophysical image processing,redundancy,hyperspectral imaging,hyperspectral images,feature selection,adaptive clone operator,multivariable mutual information (mmi),discrimination information redundancy,semi supervised learning,entropy,learning artificial intelligence | Information theory,Computer vision,Feature selection,Pattern recognition,Hyperspectral imaging,Redundancy (engineering),Artificial intelligence,Mutual information,Clonal selection algorithm,Spectral bands,Discriminative model,Mathematics | Journal |
Volume | Issue | ISSN |
53 | 5 | 0196-2892 |
Citations | PageRank | References |
17 | 0.52 | 41 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jie Feng | 1 | 247 | 20.11 |
Licheng Jiao | 2 | 5698 | 475.84 |
Fang Liu | 3 | 1188 | 125.46 |
Tao Sun | 4 | 98 | 16.37 |
Xiangrong Zhang | 5 | 493 | 48.70 |