Robust object segmentation by adaptive metrics in Generalized LVQ

We investigate the effect of several adaptive metrics in the context of figure-ground segregation, using Generalized LVQ to train a classifier for image regions. Extending the Euclidean metrics towards local matrices of relevance-factors does not only lead to a higher classification accuracy and increased robustness on heterogeneous/noisy data, but also figureground segregation using this adaptive metrics enables a considerably higher recognition performance on segmented objects of real image data.

• Type: Conference
• Year: 2008
• Where: ESANN
• Authors: Alexander Denecke, Heiko Wersing, Jochen J. Steil, Edgar Körner
• Keywords: Adaptive Metrics, ESANN 2008, Euclidean Metrics, Figure-ground Segregation, Neural Networks