A neural architecture for the symmetric-axis transform

Authors:
C. Rasche
Affiliations:
California Institute of Technology, Division of Biology, Pasadena, CA, USA and Department of Psychology, University of California Santa Barbara, Santa Barbara, CA, USA
Venue:
Neurocomputing
Year:
2005

Citing 9
Cited 0

Multiple Resolution Skeletons

IEEE Transactions on Pattern Analysis and Machine Intelligence
Hierarchical Shape Description Via the Multiresolution Symmetric Axis Transform

IEEE Transactions on Pattern Analysis and Machine Intelligence
Analog VLSI and neural systems

Analog VLSI and neural systems
Simulating the Grassfire Transform Using an Active Contour Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
A pulse-coded communications infrastructure for neuromorphic systems

Pulsed neural networks
Piecewise Linear Skeletonization Using Principal Curves

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Retinomorphic Chip with Parallel Pathways: Encoding INCREASING, ON, DECREASING, and OFF Visual Signals

Analog Integrated Circuits and Signal Processing
Signaling contours by neuromorphic wave propagation

Biological Cybernetics
Voronoi tessellation of points with integer coordinates: Time-efficient implementation and online edge-list generation

Pattern Recognition

Quantified Score

Hi-index	0.01

Visualization

Abstract

The symmetric-axis transform is a process that dynamically encodes the space of a visual shape through self-interaction of its contours. It is generally simulated using computer algorithms. A neural architecture of this transformation is presented that is conceptually simple enough for a hardware implementation. Its architecture consists of a wave-propagating map, orientation-selective columns detecting wave pieces of specific orientation, and a coincidence map detecting the clash of two wave fronts. We illustrate its operation on partial contours extracted from gray-scale images.