Ultimate Opening Segmentation with Shape Constraints

J. Hernndez and B. Marcotegui (France)

Keywords

Ultimate opening, mathematical morphology, shape infor mation, fac¸ade analysis, scene-text detection.

Abstract

In this paper, a novel method for image segmentation with shape constraints is presented. This method is based on a morphological operator named ultimate opening (UO). The UO is an operator based on numerical residues. Our ap proach introduces shape information to favor the detection of specific shapes. The method is validated in the frame work of two applications: fac¸ade analysis and scene-text detection. The experimental results show that our approach is more robust than the standard UO. Lastly, we conclude and present some perspectives of this work.

Important Links:



Go Back