Visual Grouping by Neural Oscillators

TL;DR

This paper introduces neural oscillator networks inspired by brain synchronization to improve visual grouping tasks like clustering and segmentation, demonstrating promising results in classical problems.

Contribution

It proposes a novel neural oscillator-based framework for visual grouping, integrating multi-layer and feedback mechanisms, bridging neural synchronization and computer vision.

Findings

Effective in point clustering, contour integration, and image segmentation

Achieves promising results on classical visual grouping problems

Bridges neural synchronization concepts with practical visual grouping algorithms

Abstract

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 dynamic systems, simple networks of neural oscillators coupled with diffusive connections are proposed to solve visual grouping problems. Multi-layer algorithms and feedback mechanisms are also studied. The same algorithm is shown to achieve promising results on several classical visual grouping problems, including point clustering, contour integration and image segmentation.