Open AccessComparative analysis of 2D-PCA based dimensionality reduction and feature extraction
Author(s) -
Kai Zhang,
Xiaojing Hu,
Lei Kang,
Qing Ma,
Xin Zhang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2024/1/012034
Subject(s) - dimensionality reduction , hyperspectral imaging , artificial intelligence , pattern recognition (psychology) , principal component analysis , curse of dimensionality , computer science , reduction (mathematics) , feature extraction , spatial analysis , feature (linguistics) , feature vector , mathematics , statistics , linguistics , philosophy , geometry
The complex spectral and spatial characteristics of hyperspectral remote sensing images (HSI) lead to higher time-consuming in classification task. To address this question, we introduced the 2D-PCA dimensionality reduction method of linear mapping in the two-dimensional spatial domain on the basis of linear dimensionality reduction in the spectral domain, thereby compressing the complex spatial structure information of HSI into a limited low-dimensional space, and realizing space-spectrum dimensionality reduction and information fusion. The experimental results on three classic data sets of Salinas, Tea Farm, and Indian Pines show that 2D-PCA has a strong ability to condense and compress spatial structure characteristics. Compared with popular deep learning frameworks such as CNN and Mixer-MLP, conventional machine learning models based on 2D-PCA have significant advantages in terms of computing time under the premise of controllable accuracy loss, which makes 2D-PCA a promising method for dimensionality reduction and feature expression in hyperspectral pixel-wise classification.