Massively parallel networks for edge localization and contour integration-adaptable relaxation approach

DOI10.1016/j.neunet.2003.12.001zbMath1074.68603OpenAlexW2073799059WikidataQ51699217 ScholiaQ51699217MaRDI QIDQ1883883

Toshiro Kubota

Publication date: 14 October 2004

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2003.12.001

zbMATH Keywords

VisionFeature extractionContour integrationAdaptive system

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Machine vision and scene understanding (68T45)

Cites Work

• The dynamics of nonlinear relaxation labeling processes.
• The stability and control of discrete processes
• Orientation, Scale, and Discontinuity as Emergent Properties of Illusory Contour Shape
• Spike-Timing-Dependent Hebbian Plasticity as Temporal Difference Learning
• On the Foundations of Relaxation Labeling Processes
• Scene Labeling by Relaxation Operations
• An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology

This page was built for publication: Massively parallel networks for edge localization and contour integration-adaptable relaxation approach