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

• Main Authors: Mingwei Wang, Zitong Jia, Jianwei Luo, Maolin Chen, Shuping Wang, Zhiwei Ye
• Format: Article
• Language: English
• Published: IEEE 2021-01-01
• Series: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
• Subjects: <inline-formula xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> <tex-math notation="LaTeX">$\beta$</tex-math> </inline-formula> function; ensemble learning; hyperspectral image (HSI) classification; joint sparse representation (JSR); wavelet kernel; weight setting
• Online Access: https://ieeexplore.ieee.org/document/9345341/

Joint sparse representation (JSR) is a commonly used classifier that recognizes different objects with core features extracted from images. However, the generalization ability is weak for the traditional linear kernel, and the objects with similar feature values associated with different categories are not sufficiently distinguished especially for a hyperspectral image (HSI). In this article, an HSI classification technique based on the weight wavelet kernel JSR ensemble model and the &#x03B2;-whale optimization algorithm is proposed to conduct pixel-level classification, where the 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 subclassifiers, and the &#x03B2; function is utilized to enhance the exploration phase of the whale optimization algorithm and obtain the optimal weight of subclassifiers. Experimental results indicate that the performance of the 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 all HSIs.