Online figure-ground segmentation with adaptive metrics in generalized LVQ

Authors:
Alexander Denecke;Heiko Wersing;Jochen J. Steil;Edgar Körner
Affiliations:
Bielefeld University, CoR-Lab, P.O. Box 10 01 31, D-33501 Bielefeld, Germany and Honda Research Institute Europe, Carl-Legien-Str. 30, D-63073 Offenbach/Main, Germany;Honda Research Institute Europe, Carl-Legien-Str. 30, D-63073 Offenbach/Main, Germany;Bielefeld University, CoR-Lab, P.O. Box 10 01 31, D-33501 Bielefeld, Germany;Honda Research Institute Europe, Carl-Legien-Str. 30, D-63073 Offenbach/Main, Germany
Venue:
Neurocomputing
Year:
2009

Citing 11
Cited 8

Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Generalized relevance learning vector quantization

Neural Networks - New developments in self-organizing maps
"GrabCut": interactive foreground extraction using iterated graph cuts

ACM SIGGRAPH 2004 Papers
Combining Top-Down and Bottom-Up Segmentation

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 4 - Volume 04
OBJ CUT

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A Competitive-Layer Model for Feature Binding and Sensory Segmentation

Neural Computation
Adaptive scene dependent filters for segmentation and online learning of visual objects

Neurocomputing
Robust Object Detection with Interleaved Categorization and Segmentation

International Journal of Computer Vision
Salient region detection and segmentation

ICVS'08 Proceedings of the 6th international conference on Computer vision systems
Background cut

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Learning lateral interactions for feature binding and sensory segmentation from prototypic basis interactions

IEEE Transactions on Neural Networks

Incremental Figure-Ground Segmentation Using Localized Adaptive Metrics in LVQ

WSOM '09 Proceedings of the 7th International Workshop on Advances in Self-Organizing Maps
Large-Scale Real-Time Object Identification Based on Analytic Features

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
Research on integrating different methods of neural networks with case-based reasoning and rule-based system to infer causes of notebook computer breakdown

Expert Systems with Applications: An International Journal
A biologically-inspired vision architecture for resource-constrained intelligent vehicles

Computer Vision and Image Understanding
Prototype-based classification of dissimilarity data

IDA'11 Proceedings of the 10th international conference on Advances in intelligent data analysis X
Relational extensions of learning vector quantization

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part II
White box classification of dissimilarity data

HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part I
Robust human body segmentation based on part appearance and spatial constraint

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

We address the problem of fast figure-ground segmentation of single objects from cluttered backgrounds to improve object learning and recognition. For the segmentation, we use an initial foreground hypothesis to train a classifier for figure and ground on topographically ordered feature maps with generalized learning vector quantization. We investigate the contribution of several adaptive metrics to enable generalization to the main object parts and derive a foreground classification, which yields an improved bottom-up hypothesis. We show that metrics adaptation is a powerful enrichment, where generalizing the Euclidean metrics towards local matrices of relevance factors leads to a higher classification accuracy and considerable robustness on partially inconsistent supervised information. Additionally, we verify our results in an online learning scenario and show that figure-ground segregation using this adaptive metrics enables a considerably higher recognition performance on segmented object views.