Unlocking Patterns in Hyperspectral Data: Reinforcement Learning Approach with Binary Entropy for Image Classification

Abstract

This work presents a new method for classifying hyperspectral images that combines the binary entropy technique with a Reinforcement Learning (RL) based approach. With their abundance of spectral information, hyperspectral images are an invaluable tool for remote sensing applications. The difficulty, though, is in accurately categorizing each pixel in these pictures into binary classes, like different kinds of land cover. To tackle this problem, our strategy formulates it as a Reinforcement Learning task in which an agent must learn how to determine the best thresholds for the binary entropy method. Through a reward function that promotes accurate classifications, the agent receives feedback. After preprocessing the hyperspectral data, we deploy the RL agent for real-time image classification after training and validating it. Our approach shows potential for automating thresholding and improving classification.