Automatic hierarchical clustering algorithm for remote sensing data
Valeria Sidorova · Pattern Recognition and Image Analysis · 2011
A histogram clustering algorithm is suggested, which builds the hierarchy of distributions better in cluster separability. The algorithm optimizes the average cluster separability choosing the system of the data subdomain quantization grid and allows a significant decrease in the number of clusters. Application of the algorithm for uncontrolled Earth’s surface classification by satellite spectral data is shown.