Rotationally invariant vision recognition with neuromorphic transformation and learning networks

Richard James Sofatzis; Saeed Afshar; Tara Julia Hamilton

doi:10.1109/ISCAS.2014.6865173

Rotationally invariant vision recognition with neuromorphic transformation and learning networks

Richard James Sofatzis, Saeed Afshar, Tara Julia Hamilton

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

8 Citations (Scopus)

Abstract

In this paper we present a biologically inspired rotationally-invariant end-to-end recognition system demonstrated in hardware with a bitmap camera and a Field Programmable Gate Array (FPGA). The system integrates the Ripple Pond Network (RPN), a neural network that performs image transformation from two dimensions to one dimensional rotationally invariant temporal patterns (TPs), and the Synaptic Kernel Adaptation Network (SKAN), a neural network capable of unsupervised learning of a spatio-temporal pattern of input spikes. Our results demonstrate rapid learning and recognition of simple hand gestures with no prior training and minimal usage of FPGA hardware.

Original language	English
Title of host publication	Proceedings of the 2014 IEEE International Symposium on Circuits and Systems (ISCAS 2014), Melbourne, Vic., Australia, 1-6 June 2014
Publisher	IEEE
Pages	469-472
Number of pages	4
ISBN (Print)	9781479934317
DOIs	https://doi.org/10.1109/ISCAS.2014.6865173
Publication status	Published - 2014
Event	IEEE International Symposium on Circuits and Systems - Duration: 1 Jun 2014 → …

Publication series

Name
ISSN (Print)	0271-4310

Conference

Conference	IEEE International Symposium on Circuits and Systems
Period	1/06/14 → …

Keywords

image processing
neural networks (computer science)
neuromorphics
recognition (psychology)
visual perception

Access to Document

10.1109/ISCAS.2014.6865173

Cite this

@inproceedings{37f5066d25bc47bcab917ce76a37a361,

title = "Rotationally invariant vision recognition with neuromorphic transformation and learning networks",

abstract = "In this paper we present a biologically inspired rotationally-invariant end-to-end recognition system demonstrated in hardware with a bitmap camera and a Field Programmable Gate Array (FPGA). The system integrates the Ripple Pond Network (RPN), a neural network that performs image transformation from two dimensions to one dimensional rotationally invariant temporal patterns (TPs), and the Synaptic Kernel Adaptation Network (SKAN), a neural network capable of unsupervised learning of a spatio-temporal pattern of input spikes. Our results demonstrate rapid learning and recognition of simple hand gestures with no prior training and minimal usage of FPGA hardware.",

keywords = "image processing, neural networks (computer science), neuromorphics, recognition (psychology), visual perception",

author = "Sofatzis, {Richard James} and Saeed Afshar and Hamilton, {Tara Julia}",

year = "2014",

doi = "10.1109/ISCAS.2014.6865173",

language = "English",

isbn = "9781479934317",

publisher = "IEEE",

pages = "469--472",

booktitle = "Proceedings of the 2014 IEEE International Symposium on Circuits and Systems (ISCAS 2014), Melbourne, Vic., Australia, 1-6 June 2014",

note = "IEEE International Symposium on Circuits and Systems ; Conference date: 01-06-2014",

}

Sofatzis, RJ, Afshar, S & Hamilton, TJ 2014, Rotationally invariant vision recognition with neuromorphic transformation and learning networks. in Proceedings of the 2014 IEEE International Symposium on Circuits and Systems (ISCAS 2014), Melbourne, Vic., Australia, 1-6 June 2014. IEEE, pp. 469-472, IEEE International Symposium on Circuits and Systems, 1/06/14. https://doi.org/10.1109/ISCAS.2014.6865173

Rotationally invariant vision recognition with neuromorphic transformation and learning networks. / Sofatzis, Richard James; Afshar, Saeed ; Hamilton, Tara Julia.
Proceedings of the 2014 IEEE International Symposium on Circuits and Systems (ISCAS 2014), Melbourne, Vic., Australia, 1-6 June 2014. IEEE, 2014. p. 469-472.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Rotationally invariant vision recognition with neuromorphic transformation and learning networks

AU - Sofatzis, Richard James

AU - Afshar, Saeed

AU - Hamilton, Tara Julia

PY - 2014

Y1 - 2014

N2 - In this paper we present a biologically inspired rotationally-invariant end-to-end recognition system demonstrated in hardware with a bitmap camera and a Field Programmable Gate Array (FPGA). The system integrates the Ripple Pond Network (RPN), a neural network that performs image transformation from two dimensions to one dimensional rotationally invariant temporal patterns (TPs), and the Synaptic Kernel Adaptation Network (SKAN), a neural network capable of unsupervised learning of a spatio-temporal pattern of input spikes. Our results demonstrate rapid learning and recognition of simple hand gestures with no prior training and minimal usage of FPGA hardware.

AB - In this paper we present a biologically inspired rotationally-invariant end-to-end recognition system demonstrated in hardware with a bitmap camera and a Field Programmable Gate Array (FPGA). The system integrates the Ripple Pond Network (RPN), a neural network that performs image transformation from two dimensions to one dimensional rotationally invariant temporal patterns (TPs), and the Synaptic Kernel Adaptation Network (SKAN), a neural network capable of unsupervised learning of a spatio-temporal pattern of input spikes. Our results demonstrate rapid learning and recognition of simple hand gestures with no prior training and minimal usage of FPGA hardware.

KW - image processing

KW - neural networks (computer science)

KW - neuromorphics

KW - recognition (psychology)

KW - visual perception

UR - http://handle.uws.edu.au:8081/1959.7/uws:28854

UR - http://iscas2014.org/

U2 - 10.1109/ISCAS.2014.6865173

DO - 10.1109/ISCAS.2014.6865173

M3 - Conference Paper

SN - 9781479934317

SP - 469

EP - 472

BT - Proceedings of the 2014 IEEE International Symposium on Circuits and Systems (ISCAS 2014), Melbourne, Vic., Australia, 1-6 June 2014

PB - IEEE

T2 - IEEE International Symposium on Circuits and Systems

Y2 - 1 June 2014

ER -

Rotationally invariant vision recognition with neuromorphic transformation and learning networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this