Simulation of Visual Attention using Hierarchical Spiking Neural Networks

Qingxiang Wu; TM McGinnity; LP Maguire; Rongtai Cai; Meigui Chen

Simulation of Visual Attention using Hierarchical Spiking Neural Networks

Qingxiang Wu, TM McGinnity, LP Maguire, Rongtai Cai, Meigui Chen

Faculty Of Computing, Eng. & Built Env.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

Based on the information processing functionalities of spiking neurons, a hierarchical spiking neural network model is proposed to simulate visual attention. The network is constructed with a conductance-based integrate-and-fire neuron model and a set of specific receptive fields in different levels. The simulation algorithm and properties of the network are detailed in this paper. Simulation results show that the network is able to perform visual attention to extract objects based on specific image features. Using extraction of horizontal and vertical lines, a demonstration shows how the network can detect a house in a visual image. Using this visual attention principle, many other objects can be extracted by analogy.

Original language	English
Title of host publication	Unknown Host Publication
Place of Publication	Berlin Heidelberg
Publisher	Springer
Pages	26-31
Number of pages	6
Volume	6840
ISBN (Print)	978-3-642-24552-7
Publication status	Published (in print/issue) - 4 Oct 2011
Event	International Conference on Interlligent Computing (ICIC 2011) - Duration: 4 Oct 2011 → …

Conference

Conference	International Conference on Interlligent Computing (ICIC 2011)
Period	4/10/11 → …

Keywords

Visual attention
spiking neural network
receptive field
visual system.

Access to Document

Cite this

@inproceedings{d472df68b06d4c49a73bcf5b4ebb8859,

title = "Simulation of Visual Attention using Hierarchical Spiking Neural Networks",

abstract = "Based on the information processing functionalities of spiking neurons, a hierarchical spiking neural network model is proposed to simulate visual attention. The network is constructed with a conductance-based integrate-and-fire neuron model and a set of specific receptive fields in different levels. The simulation algorithm and properties of the network are detailed in this paper. Simulation results show that the network is able to perform visual attention to extract objects based on specific image features. Using extraction of horizontal and vertical lines, a demonstration shows how the network can detect a house in a visual image. Using this visual attention principle, many other objects can be extracted by analogy.",

keywords = "Visual attention, spiking neural network, receptive field, visual system.",

author = "Qingxiang Wu and TM McGinnity and LP Maguire and Rongtai Cai and Meigui Chen",

year = "2011",

month = oct,

day = "4",

language = "English",

isbn = "978-3-642-24552-7",

volume = "6840",

pages = "26--31",

booktitle = "Unknown Host Publication",

publisher = "Springer",

address = "Switzerland",

note = "International Conference on Interlligent Computing (ICIC 2011) ; Conference date: 04-10-2011",

}

TY - GEN

T1 - Simulation of Visual Attention using Hierarchical Spiking Neural Networks

AU - Wu, Qingxiang

AU - McGinnity, TM

AU - Maguire, LP

AU - Cai, Rongtai

AU - Chen, Meigui

PY - 2011/10/4

Y1 - 2011/10/4

N2 - Based on the information processing functionalities of spiking neurons, a hierarchical spiking neural network model is proposed to simulate visual attention. The network is constructed with a conductance-based integrate-and-fire neuron model and a set of specific receptive fields in different levels. The simulation algorithm and properties of the network are detailed in this paper. Simulation results show that the network is able to perform visual attention to extract objects based on specific image features. Using extraction of horizontal and vertical lines, a demonstration shows how the network can detect a house in a visual image. Using this visual attention principle, many other objects can be extracted by analogy.

AB - Based on the information processing functionalities of spiking neurons, a hierarchical spiking neural network model is proposed to simulate visual attention. The network is constructed with a conductance-based integrate-and-fire neuron model and a set of specific receptive fields in different levels. The simulation algorithm and properties of the network are detailed in this paper. Simulation results show that the network is able to perform visual attention to extract objects based on specific image features. Using extraction of horizontal and vertical lines, a demonstration shows how the network can detect a house in a visual image. Using this visual attention principle, many other objects can be extracted by analogy.

KW - Visual attention

KW - spiking neural network

KW - receptive field

KW - visual system.

M3 - Conference contribution

SN - 978-3-642-24552-7

VL - 6840

SP - 26

EP - 31

BT - Unknown Host Publication

PB - Springer

CY - Berlin Heidelberg

T2 - International Conference on Interlligent Computing (ICIC 2011)

Y2 - 4 October 2011

ER -

Simulation of Visual Attention using Hierarchical Spiking Neural Networks

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this