User: Guest  Login
Title:

Morphological Proximity Priors: Spatial Relationships for Semantic Segmentation

Document type:
Report / Forschungsbericht
Author(s):
Julia Bergbauer, Claudia Nieuwenhuis, Mohamed Souiai, Daniel Cremers
Abstract:
The introduction of prior knowledge into image analysis algorithms is a central challenge in computer vision. In this paper, we introduce the concept of proximity priors into semantic segmentation methods in order to penalize the proximity of certain object classes. Proximity priors are a generalization of purely global and purely local co-occurrence priors which have been introduced recently. The key idea is to consider pixels as adjacent if they are within a specified neighborhood of arbitrary...     »
Keywords:
Multi Label Segmentation, Convex Relaxation, Co-Occurrence, Higher Order Priors, Convex Optimization
Year:
2013
Language:
en
Format:
Text
 BibTeX
versions