A Visual Attention Model Based on Hierarchical Spiking Neural Networks

Q Wu, TM McGinnity, LP Maguire, R Cai, M Chen

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Based on the information processing functionalities of spiking neurons, hierarchical spiking neural networks are proposed to simulate visual attention. Using spiking neural networks inspired by the visual system, an image can be decomposed into multiple visual image components. Based on specific visual image components and image features, a visual attention system is proposed to extract attention areas according to top-down volition-controlled signals. The hierarchical spiking neural networks are 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 networks are detailed in this paper. Simulation results show that the attention system is able to perform visual attention of objects based on specific image components or features, and a demonstration shows how the attention system can detect a house in a visual image. Using the proposed saliency index, attention areas of interest can be extracted from spike rate maps of multiple visual pathways, such as ON/OFF colour pathways. According to this visual attention principle, the visual image processing system can quickly focus on specific areas while ignoring other areas.
LanguageEnglish
Pages3-12
JournalNeurocomputing
Volume116
DOIs
Publication statusPublished - 2013

Fingerprint

Neural networks
Neurons
Fires
Image processing
Demonstrations
Color
Visual Pathways
Automatic Data Processing

Cite this

@article{a4fb294a3a0b400db0b191ab5147042c,
title = "A Visual Attention Model Based on Hierarchical Spiking Neural Networks",
abstract = "Based on the information processing functionalities of spiking neurons, hierarchical spiking neural networks are proposed to simulate visual attention. Using spiking neural networks inspired by the visual system, an image can be decomposed into multiple visual image components. Based on specific visual image components and image features, a visual attention system is proposed to extract attention areas according to top-down volition-controlled signals. The hierarchical spiking neural networks are 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 networks are detailed in this paper. Simulation results show that the attention system is able to perform visual attention of objects based on specific image components or features, and a demonstration shows how the attention system can detect a house in a visual image. Using the proposed saliency index, attention areas of interest can be extracted from spike rate maps of multiple visual pathways, such as ON/OFF colour pathways. According to this visual attention principle, the visual image processing system can quickly focus on specific areas while ignoring other areas.",
author = "Q Wu and TM McGinnity and LP Maguire and R Cai and M Chen",
year = "2013",
doi = "10.1016/j.neucom.2012.01.046",
language = "English",
volume = "116",
pages = "3--12",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

A Visual Attention Model Based on Hierarchical Spiking Neural Networks. / Wu, Q; McGinnity, TM; Maguire, LP; Cai, R; Chen, M.

In: Neurocomputing, Vol. 116, 2013, p. 3-12.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Visual Attention Model Based on Hierarchical Spiking Neural Networks

AU - Wu, Q

AU - McGinnity, TM

AU - Maguire, LP

AU - Cai, R

AU - Chen, M

PY - 2013

Y1 - 2013

N2 - Based on the information processing functionalities of spiking neurons, hierarchical spiking neural networks are proposed to simulate visual attention. Using spiking neural networks inspired by the visual system, an image can be decomposed into multiple visual image components. Based on specific visual image components and image features, a visual attention system is proposed to extract attention areas according to top-down volition-controlled signals. The hierarchical spiking neural networks are 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 networks are detailed in this paper. Simulation results show that the attention system is able to perform visual attention of objects based on specific image components or features, and a demonstration shows how the attention system can detect a house in a visual image. Using the proposed saliency index, attention areas of interest can be extracted from spike rate maps of multiple visual pathways, such as ON/OFF colour pathways. According to this visual attention principle, the visual image processing system can quickly focus on specific areas while ignoring other areas.

AB - Based on the information processing functionalities of spiking neurons, hierarchical spiking neural networks are proposed to simulate visual attention. Using spiking neural networks inspired by the visual system, an image can be decomposed into multiple visual image components. Based on specific visual image components and image features, a visual attention system is proposed to extract attention areas according to top-down volition-controlled signals. The hierarchical spiking neural networks are 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 networks are detailed in this paper. Simulation results show that the attention system is able to perform visual attention of objects based on specific image components or features, and a demonstration shows how the attention system can detect a house in a visual image. Using the proposed saliency index, attention areas of interest can be extracted from spike rate maps of multiple visual pathways, such as ON/OFF colour pathways. According to this visual attention principle, the visual image processing system can quickly focus on specific areas while ignoring other areas.

U2 - 10.1016/j.neucom.2012.01.046

DO - 10.1016/j.neucom.2012.01.046

M3 - Article

VL - 116

SP - 3

EP - 12

JO - Neurocomputing

T2 - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -