A Hyperspectral Image Classification Method Based on Weight Wavelet Kernel Joint Sparse Representation Ensemble and β-Whale Optimization Algorithm

Abstract

Joint sparse representation (JSR) is a commonly used classifier to recognize different objects with core features extracted from images. However, the generalization ability is weak for traditional linear kernel, and the objects with similar feature values affiliated to different categories are not enough distinguished especially for hyperspectral image (HSI). In the paper, a HSI classification technique based on weight wavelet kernel JSR ensemble (W 2 JSRE) model and β-whale optimization algorithm (WOA) is proposed to conduct pixel-level classification, where wavelet function is acted as the kernel of JSR. Moreover, ensemble learning is used to determine the category label of each sample by comprehensive decision of some sub-classifiers, and β function is utilized to enhance the exploration phase of WOA and obtain the optimal weight of sub-classifiers. Experimental results indicate that the performance of proposed HSI classification method is better than that of other newly proposed and corresponding approaches, the misclassification and classified noise are eliminated to some extent, and the overall classification accuracy reaches 95% for entire HSIs.

Efficient Classification of Hyperspectral Image s Using Multiscale Relation Learning

“…The 2021 paper by Bishwas Praveen and Vineetha Menon presents a deep learning framework for categorization of robust hyperspectral data. The framework achieves better classification performance by effectively combining spectral and spatial information [3]. The system applies supervised classification with a 3-D convolutional neural network, using sparse random projections for spectral feature extraction and Gabor filtering for spatial feature extraction.…”

Improved whale optimization algorithm and its application in heterogeneous wireless sensor networks

“…23 Assuming that the individual with the smallest fitness value in the current population is the target prey, other whales update their positions according to this position. The mathematical model at this stage is as follows 24…”

Hyperspectral detection of walnut protein contents based on improved whale optimized algorithm

“…While in the process of feature selection using WOA, most studies only adopted random principle to set up whale foraging behaviors, which makes the selected features mostly dependent on the performance of WOA and does not fully consider the contribution of hyperspectral characteristics including amplitude and shape information in feature selection [30] . Besides, for variable selection, there are three factors which are quite important to be considered.…”