Global Segmentation of Textural Images on the Basis of Hierarchical Clusterization by Predetermined Cluster Separability

摘要

Automatic clusterization and follow segmentation of aerial pictures images by textural features is are considered. A divisible histogram hierarchical algorithm with search of clusters with preset separability is used. The peculiarity of segmentation by statistical textural features are taken into account. The parameters of the model for SAR imaging are used as textural features for automatic uncontrolled classification of forest landscapes in aerial images.