Hierarchical Finite-State Modeling for Texture Segmentation with Application to Forest Classification

0080583 - ÚTIA 2007 FR eng V - Výzkumná zpráva
Scarpa, G. - Haindl, Michal - Zerubia, J.
Hierarchical Finite-State Modeling for Texture Segmentation with Application to Forest Classification.
Sophia Antipolis: Institut National de Recherche en Informatique et en Automatique, 2006. 47 s. Rapport de recherche, 6066. ISSN 0249-6399
GRANT EU: European Commission(XE) 507752 - MUSCLE
Výzkumný záměr: CEZ:AV0Z10750506
Klíčová slova: Texture segmentation * classification * co-occurrence matrix * structural models * Markov chain * texture synthesis * forest classification
Kód oboru RIV: BD - Teorie informace
http://hal.inria.fr/inria-00118420/en/

In this research report we present a new model for texture representation which is particularly well suited for image analysis and segmentation. Any image is first discretized and then a hierarchical finite-state region-based model is automatically coupled with the data by means of a sequential optimization scheme, namely the Texture Fragmentation and Reconstruction (TFR) algorithm. The TFR algorithm allows to model both intra- and inter-texture interactions, and eventually addresses the segmentation task in a completely unsupervised manner. Moreover, it provides a hierarchical output, as the user may decide the scale at which the segmentation has to be given. Tests were carried out on both natural texture mosaics provided by the Prague Texture Segmentation Datagenerator Benchmark and remote-sensing data of forest areas provided by the French National Forest Inventory (IFN).

Viz. anglická anotace.
Trvalý link: http://hdl.handle.net/11104/0144715