Document Type

Conference Proceeding

Publisher

IEEE

Faculty

Faculty of Computing, Health and Science

School

School of Engineering and Mathematics

RAS ID

3402

Comments

This is an Author's Accepted Manuscript of: Crebbin, G. A. (2005). Image segmentation using neuromorphic integrate and fire cells. Proceedings of 2005 Fifth International Conference on Information, Communications and Signal Processing (ICICS 2005). (pp. 305-309). Bangkok. IEEE. Available here

© 2005 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Abstract

This paper introduces an electronic circuit implementation of an integrate-and-fire cell. The cell generates output current pulses when the input light intensity exceeds a given threshold. A firing cell also transmits its firing pattern to neighbouring cells, thereby causing blocks of cells to fire in synchrony when their detectors receive similar input light intensities. The synchronicity and frequency of the pulses can be used to code an image into separate regions or objects. The actions of the cell are demonstrated with the simulation of a linear 8-cell array

DOI

10.1109/ICICS.2005.1689056

Access Rights

free_to_read

Included in

Engineering Commons

Share

 
COinS
 

Link to publisher version (DOI)

10.1109/ICICS.2005.1689056