Optimized Hyperspectral Image Classification Using Tabu Search for Band Selection and Hyper3DNet Lite Classifier

Abstract

Hyperspectral imaging (HSI) is essential for capturing images across various spectral bands and providing in-depth spectral information. However, the high dimensionality of HSI data presents challenges, such as increased computational complexity and the curse of dimensionality. Band selection is a critical pre-processing step that addresses these challenges by identifying the most informative bands. This paper introduces a novel band selection method utilizing the Tabu Search algorithm (TSA), aimed at optimizing the selection of spectral bands to enhance classification performance. The proposed method assesses bands using a fitness function that maximizes variance and minimizes correlation among the chosen bands. Experimental results on Indian pine dataset and Pavia University Scenes, along with the K-Nearest Neighbor and Support Vector machine improves the classification accuracy while reducing computational demands.