Dec 17, 2013 · In this paper, a novel criterion based on trivariate MI (TMI) is proposed to measure the redundancy for classification.
Band selection is an important preprocessing step for hyperspectral data processing. It involves two crucial problems, i.e., suitable measure criterion and ...
Experimental results demonstrate the effectiveness of the proposed algorithms for hy- perspectral band selection. Index Terms—Clonal selection algorithm (CSA), ...
People also ask
What are the methods of hyperspectral feature selection?
What is band selection in hyperspectral image classification?
Jun 18, 2019 · One of the most important preprocessing steps for HSI analysis is dimensionality re- duction, which aims to remove spectral redundancy while.
Jun 15, 2022 · Band selection is one of the main methods of reducing the number of dimensions in a hyperspectral image. Recently, various methods have been ...
The proposed approach utilizes an unsupervised feature selection technique based on the information theory measures, mutual information and entropy. Spatial ...
Experimental results evidence for the superiority of the proposed approach over the recent multi-objective optimization-based band selection approaches by ...
This paper proposes a novel multi-objective optimization model based framework for band selection, in which different optimal trade-offs between information ...
This paper presents a spatial spectral mutual information (SSMI) BS scheme that utilizes a spatial feature extraction technique as a preprocessing step.
Article: Mutual-Information-Based Semi-Supervised Hyperspectral Band Selection With High Discrimination, High Information, and Low Redundancy.