A segmentation quality measure based on rich descriptors and classification methods

Authors:
David Peles;Michael Lindenbaum
Affiliations:
Computer Science Department, Technion, Haifa, Israel;Computer Science Department, Technion, Haifa, Israel
Venue:
SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
Year:
2011

Citing 12
Cited 0

Topographic distance and watershed lines

Signal Processing - Special issue on mathematical morphology and its applications to signal processing
Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning a Classification Model for Segmentation

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues

IEEE Transactions on Pattern Analysis and Machine Intelligence
"GrabCut": interactive foreground extraction using iterated graph cuts

ACM SIGGRAPH 2004 Papers
Aggregating inconsistent information: ranking and clustering

Proceedings of the thirty-seventh annual ACM symposium on Theory of computing
Supervised Learning of Edges and Object Boundaries

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
What Is a Good Image Segment? A Unified Approach to Segment Extraction

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part IV
Optimizing Gabor Filter Design for Texture Edge Detection and Classification

International Journal of Computer Vision
Active contours without edges

IEEE Transactions on Image Processing
ScribbleBoost: adding classification to edge-aware interpolation of local image and video adjustments

EGSR'08 Proceedings of the Nineteenth Eurographics conference on Rendering

Quantified Score

Hi-index	0.00

Visualization

Abstract

Most segmentation methods are based on a relatively simple score, designed to lend itself to relatively efficient optimization. We take the opposite approach and suggest more complex segmentation scores that are based on a mixture of on-line and off-line learning processes and rely on rich descriptors. The score is evaluated by a segmentation process which uses exploration-exploitation to search for good segments in various scales and shapes. We test our algorithm in a foreground-background segmentation task, given a minimal prior which is just a single seed point inside the object of interest. Results on two image databases are presented and compared with earlier approaches.