Model driven image segmentation using a genetic algorithm for structured data

Authors:
Romain Raveaux;Guillaume Hillairet
Affiliations:
L3I, University of La Rochelle, La Rochelle Cedex 1, France;L3I, University of La Rochelle, La Rochelle Cedex 1, France
Venue:
HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part I
Year:
2010

Citing 3
Cited 0

A generic arc-consistency algorithm and its specializations

Artificial Intelligence
Constraint satisfaction problem with bilevel constraint: application to interpretation of over-segmented images

Artificial Intelligence
On a relation between graph edit distance and maximum common subgraph

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a method, integrating efficiently a semantic approach into an image segmentation process, is proposed A graph based representation is exploited to carry out this knowledge integration Firstly, a watershed segmentation is roughly performed From this raw partition into regions an adjacency graph is extracted A model transformation turns this syntaxic structure into a semantic model Then the consistence of the computer-generated model is compared to the user-defined model A genetic algorithm optimizes the region merging mechanism to fit the ground-truth model The efficiency of our system is assessed on real images.