Guided informative image partitioning

Authors:
Nathan Brewer;Nianjun Liu;Lei Wang
Affiliations:
College of Engineering and Computer Science, Australian National University, Canberra, Australia and Canberra Research Laboratory, NICTA, Canberra, Australia;Canberra Research Laboratory, NICTA, Canberra, Australia;College of Engineering and Computer Science, Australian National University, Canberra, Australia
Venue:
SSPR&SPR'10 Proceedings of the 2010 joint IAPR international conference on Structural, syntactic, and statistical pattern recognition
Year:
2010

Citing 8
Cited 0

Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Markov random field modeling in image analysis

Markov random field modeling in image analysis
Classifying Images of Materials: Achieving Viewpoint and Illumination Independence

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Efficient Graph-Based Image Segmentation

International Journal of Computer Vision
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision

IEEE Transactions on Pattern Analysis and Machine Intelligence
Guiding Model Search Using Segmentation

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Semi-supervised statistical region refinement for color image segmentation

Pattern Recognition
TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Image partitioning separates an image into multiple visually and semantically homogeneous regions, providing a summary of visual content. Knowing that human observers focus on interesting objects or regions when interpreting a scene, and envisioning the usefulness of this focus in many computer vision tasks, this paper develops a userattention adaptive image partitioning approach. Given a set of pairs of oversegments labeled by a user as "should be merged" or "should not be merged", the proposed approach produces a fine partitioning in user defined interesting areas, to retain interesting information, and a coarser partitioning in other regions to provide a parsimonious representation. To achieve this, a novel Markov Random Field (MRF) model is used to optimally infer the relationship ("merge" or "not merge") among oversegment pairs, by using the graph nodes to describe the relationship between pairs. By training an SVM classifier to provide the data term, a graph-cut algorithm is employed to infer the best MRF configuration. We discuss the difficulty in translating this configuration back to an image labelling, and develop a non-trivial post-processing to refine the configuration further. Experimental verification on benchmark data sets demonstrates the effectiveness of the proposed approach.