Wishart Clustering with Polarimetric Entropy, Scattering Angle, and Anisotropy

This implementation features Wishart clustering utilizing polarimetric entropy, scattering angle, and anisotropy parameters, accompanied by a dedicated Freeman decomposition code. These algorithms find applications across multiple domains including remote sensing image analysis, signal processing, and pattern recognition. Polarimetric entropy serves as a key metric for quantifying the complexity of polarimetric images, enabling enhanced characterization of polarimetric information through entropy-based feature extraction. The scattering angle parameter provides critical insights into polarimetric signal scattering behavior, with analytical routines designed to extract target-specific information through angle distribution analysis. The Wishart clustering algorithm incorporates anisotropy measures to segment polarimetric data into meaningful clusters, employing covariance matrix analysis to identify hidden patterns and structural relationships within the data. The supplementary Freeman decomposition code implements a three-component scattering model (surface, double-bounce, and volume scattering) for targeted feature extraction in image analysis applications. Through these integrated methods, researchers can achieve deeper insights into polarimetric data characteristics and obtain superior results in practical implementations.