Hyperspectral image classification based on average spectral-spatial features and improved hierarchical-ELM

Le, Ba Tuan; Ha, Thai Thuy Lam

doi:10.1016/j.infrared.2019.103013

Cited by 14 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The further different algorithms were then compared with seven benchmark algorithms; namely, ELM, kernel ELM (KELM), weighted KELM (WKELM), the spatial feature that uses guided filtering features combined with KELM (SS-KELM), KELM-CK (extreme learning machine e-composite kernel) [21], ASS-H-DELM (average spectral-spatial hierarchical extreme learning machine) [28], and HCKBoost (hybridized composite kernel boosting with extreme learning machines) [27].…”

Section: Accuracy Of Classification and Analysismentioning

confidence: 99%

“…Ensemble learning based method was also developed for hyperspectral imagery classification, Ugur Ergul [27] proposed a new boosting-based algorithm, which enables the construction of composite kernels (CKs) by using spatial and spectral hybrid kernels. In [28], an improved hierarchical ELM was designed by adding an ELM to a hierarchical ELM. In this model, the average spectral-spatial features were extracted twice by this multiple layer framework; satisfactory results were achieved.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dual-Weighted Kernel Extreme Learning Machine for Hyperspectral Imagery Classification

et al. 2021

View full text Add to dashboard Cite

Due to its excellent performance in high-dimensional space, the kernel extreme learning machine has been widely used in pattern recognition and machine learning fields. In this paper, we propose a dual-weighted kernel extreme learning machine for hyperspectral imagery classification. First, diverse spatial features are extracted by guided filtering. Then, the spatial features and spectral features are composited by a weighted kernel summation form. Finally, the weighted extreme learning machine is employed for the hyperspectral imagery classification task. This dual-weighted framework guarantees that the subtle spatial features are extracted, while the importance of minority samples is emphasized. Experiments carried on three public data sets demonstrate that the proposed dual-weighted kernel extreme learning machine (DW-KELM) performs better than other kernel methods, in terms of accuracy of classification, and can achieve satisfactory results.

show abstract

Section: Accuracy Of Classification and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%