Visual Grouping by Neural Oscillator Networks
Author(s)Yu, Guoshen; Slotine, Jean-Jacques E.
MetadataShow full item record
Distributed synchronization is known to occur at several scales in the brain, and has been suggested as playing a key functional role in perceptual grouping. State-of-the-art visual grouping algorithms, however, seem to give comparatively little attention to neural synchronization analogies. Based on the framework of concurrent synchronization of dynamical systems, simple networks of neural oscillators coupled with diffusive connections are proposed to solve visual grouping problems. The key idea is to embed the desired grouping properties in the choice of the diffusive couplings, so that synchronization of oscillators within each group indicates perceptual grouping of the underlying stimulative atoms, while desynchronization between groups corresponds to group segregation. Compared with state-of-the-art approaches, the same algorithm is shown to achieve promising results on several classical visual grouping problems, including point clustering, contour integration, and image segmentation.
DepartmentMassachusetts Institute of Technology. Department of Mechanical Engineering
IEEE Transactions on Neural Networks
Institute of Electrical and Electronics Engineers
Guoshen Yu, and J.-J. Slotine. “Visual Grouping by Neural Oscillator Networks.” Neural Networks, IEEE Transactions on 20.12 (2009): 1871-1884. © 2009 IEEE
Final published version
vision, synchronization, neural oscillator, image segmentation, Grouping