You are here

Joint image segmentation and interpretation using iterative semantic region growing on SAR sea ice imagery

TitleJoint image segmentation and interpretation using iterative semantic region growing on SAR sea ice imagery
Publication TypeConference Paper
Year of Publication2006
AuthorsYu, Q., and D. A. Clausi
Conference Name18th International Conference on Pattern Recognition (ICPR)
Date Published08/2006
Conference LocationHong Kong
KeywordsBayes methods, Bayesian framework, image analysis, image classification, image interpretation, image segmentation, iterative methods, iterative semantic region growing, Markov processes, Markov random field based classification, radar imaging, SAR sea ice imagery, sea ice, semantic class labels, synthetic aperture radar, terrain mapping
Abstract

Segmentation of images into disjoint regions and interpretation of the regions for semantic meanings are two central tasks in an image analysis system. Typically, the segmentation and interpretation are performed separately with the interpretation as a post processing of segmentation. In this paper, we use an iterative method that keeps refining the segmentation and producing semantic class labels at the same time. The segmentation algorithm is based on a region growing technique and the interpretation is a Markov random field (MRF) based classification. The two processes are integrated under the Bayesian framework, with both aiming at reducing a defined energy. The interactions between the two are bidirectional by letting the interpretation result have some degree of control on the region growing process. Various features can hence be efficiently combined, and accurate classifications are obtained for operational synthetic aperture radar (SAR) sea ice applications

DOI10.1109/ICPR.2006.734