Colour Image Segmentation Based on a Spiking Neural Network Model Inspired by the Visual System

Qingxiang Wu; TM McGinnity; Liam Maguire; German Valderrama; Patrick Dempster

doi:10.1007/978-3-642-14922-1_7

Colour Image Segmentation Based on a Spiking Neural Network Model Inspired by the Visual System

Qingxiang Wu
, TM McGinnity
, Liam Maguire
, German Valderrama
, Patrick Dempster

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

14 Citations (Scopus)

Abstract

The human visual system demonstrates powerful image processing functionalities. Inspired by the visual system, a spiking neural network is proposed to segment visual images. The network is constructed in the two parts. The first part is a spiking neural network which is composed of photon receptors, cone and rod cells, and ON/OFF ganglion cells. Colour features can be extracted and passed through different ON/OFF pathways. The second part is a BP neural network which is trained to recognize the colour features and segment the visual image. The network has been successfully applied to segment leukocytes from blood smeared images.

Original language	English
Title of host publication	Unknown Host Publication
Editors	D.-S. Huang
Place of Publication	Berlin Heidelberg
Publisher	Springer
Pages	49-57
Number of pages	8
DOIs	https://doi.org/10.1007/978-3-642-14922-1_7
Publication status	Published (in print/issue) - 1 Aug 2010
Event	international conference on Intelligent Computing (ICIC2010) - Changsha, China Duration: 1 Aug 2010 → …

Conference

Conference	international conference on Intelligent Computing (ICIC2010)
Period	1/08/10 → …

Keywords

Spiking neural networks
image segmentation
visual system
visual image

Access to Document

10.1007/978-3-642-14922-1_7

Cite this

@inproceedings{3b7f88ce2e7f4d27974ac7890190f722,

title = "Colour Image Segmentation Based on a Spiking Neural Network Model Inspired by the Visual System",

abstract = "The human visual system demonstrates powerful image processing functionalities. Inspired by the visual system, a spiking neural network is proposed to segment visual images. The network is constructed in the two parts. The first part is a spiking neural network which is composed of photon receptors, cone and rod cells, and ON/OFF ganglion cells. Colour features can be extracted and passed through different ON/OFF pathways. The second part is a BP neural network which is trained to recognize the colour features and segment the visual image. The network has been successfully applied to segment leukocytes from blood smeared images.",

keywords = "Spiking neural networks, image segmentation, visual system, visual image",

author = "Qingxiang Wu and TM McGinnity and Liam Maguire and German Valderrama and Patrick Dempster",

year = "2010",

month = aug,

day = "1",

doi = "10.1007/978-3-642-14922-1\_7",

language = "English",

pages = "49--57",

editor = "D.-S. Huang",

booktitle = "Unknown Host Publication",

publisher = "Springer",

address = "Switzerland",

note = "international conference on Intelligent Computing (ICIC2010) ; Conference date: 01-08-2010",

}

TY - GEN

T1 - Colour Image Segmentation Based on a Spiking Neural Network Model Inspired by the Visual System

AU - Wu, Qingxiang

AU - McGinnity, TM

AU - Maguire, Liam

AU - Valderrama, German

AU - Dempster, Patrick

PY - 2010/8/1

Y1 - 2010/8/1

N2 - The human visual system demonstrates powerful image processing functionalities. Inspired by the visual system, a spiking neural network is proposed to segment visual images. The network is constructed in the two parts. The first part is a spiking neural network which is composed of photon receptors, cone and rod cells, and ON/OFF ganglion cells. Colour features can be extracted and passed through different ON/OFF pathways. The second part is a BP neural network which is trained to recognize the colour features and segment the visual image. The network has been successfully applied to segment leukocytes from blood smeared images.

AB - The human visual system demonstrates powerful image processing functionalities. Inspired by the visual system, a spiking neural network is proposed to segment visual images. The network is constructed in the two parts. The first part is a spiking neural network which is composed of photon receptors, cone and rod cells, and ON/OFF ganglion cells. Colour features can be extracted and passed through different ON/OFF pathways. The second part is a BP neural network which is trained to recognize the colour features and segment the visual image. The network has been successfully applied to segment leukocytes from blood smeared images.

KW - Spiking neural networks

KW - image segmentation

KW - visual system

KW - visual image

UR - http://www.springerlink.com/content/3406131q37089x37/

U2 - 10.1007/978-3-642-14922-1_7

DO - 10.1007/978-3-642-14922-1_7

M3 - Conference contribution

SP - 49

EP - 57

BT - Unknown Host Publication

A2 - Huang, D.-S.

PB - Springer

CY - Berlin Heidelberg

T2 - international conference on Intelligent Computing (ICIC2010)

Y2 - 1 August 2010

ER -

Colour Image Segmentation Based on a Spiking Neural Network Model Inspired by the Visual System

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this