Spiking neural network performs discrete cosine transform for visual images

Qingxiang Wu, T. M. McGinnity, Liam Maguire, Arfan Ghani, Joan Condell

Research output: Chapter in Book/Report/Conference proceedingChapter

5 Citations (Scopus)

Abstract

The human visual system demonstrates powerful image processing functionalities. Inspired by the principles from neuroscience, a spiking neural network is proposed to perform the discrete cosine transform for visual images. The structure and the properties of the network are detailed in this paper. Simulation results show that the network is able to perform the discrete cosine transform for visual images. Based on this mechanism, the key features can be extracted in ON/OFF neuron arrays. These key features can be used to reconstruct the visual images. The network can be used to explain how the spiking neuron-based system can perform key feature extraction. The differences between the discrete cosine transform and the spiking neural network transform are discussed.
Original languageEnglish
Title of host publicationEmerging Intelligent Computing Technology and Applications
Subtitle of host publicationWith Aspects of Artificial Intelligence
PublisherSpringer Verlag
Pages21-29
Number of pages9
ISBN (Print)97836420402073
DOIs
Publication statusPublished - 2009

Fingerprint

Discrete cosine transforms
Neural networks
Neurons
Feature extraction
Image processing

Keywords

  • spiking neural networks
  • visual system
  • discrete cosine transform
  • visual image

Cite this

Wu, Q., McGinnity, T. M., Maguire, L., Ghani, A., & Condell, J. (2009). Spiking neural network performs discrete cosine transform for visual images. In Emerging Intelligent Computing Technology and Applications: With Aspects of Artificial Intelligence (pp. 21-29). Springer Verlag. https://doi.org/10.1007/978-3-642-04020-7_3

Spiking neural network performs discrete cosine transform for visual images. / Wu, Qingxiang ; McGinnity, T. M.; Maguire, Liam; Ghani, Arfan; Condell, Joan .

Emerging Intelligent Computing Technology and Applications: With Aspects of Artificial Intelligence. Springer Verlag, 2009. p. 21-29.

Research output: Chapter in Book/Report/Conference proceedingChapter

Wu, Q, McGinnity, TM, Maguire, L, Ghani, A & Condell, J 2009, Spiking neural network performs discrete cosine transform for visual images. in Emerging Intelligent Computing Technology and Applications: With Aspects of Artificial Intelligence. Springer Verlag, pp. 21-29. https://doi.org/10.1007/978-3-642-04020-7_3
Wu Q, McGinnity TM, Maguire L, Ghani A, Condell J. Spiking neural network performs discrete cosine transform for visual images. In Emerging Intelligent Computing Technology and Applications: With Aspects of Artificial Intelligence. Springer Verlag. 2009. p. 21-29 https://doi.org/10.1007/978-3-642-04020-7_3
Wu, Qingxiang ; McGinnity, T. M. ; Maguire, Liam ; Ghani, Arfan ; Condell, Joan . / Spiking neural network performs discrete cosine transform for visual images. Emerging Intelligent Computing Technology and Applications: With Aspects of Artificial Intelligence. Springer Verlag, 2009. pp. 21-29
@inbook{b74ddddae504420dab3ea7b1f438b087,
title = "Spiking neural network performs discrete cosine transform for visual images",
abstract = "The human visual system demonstrates powerful image processing functionalities. Inspired by the principles from neuroscience, a spiking neural network is proposed to perform the discrete cosine transform for visual images. The structure and the properties of the network are detailed in this paper. Simulation results show that the network is able to perform the discrete cosine transform for visual images. Based on this mechanism, the key features can be extracted in ON/OFF neuron arrays. These key features can be used to reconstruct the visual images. The network can be used to explain how the spiking neuron-based system can perform key feature extraction. The differences between the discrete cosine transform and the spiking neural network transform are discussed.",
keywords = "spiking neural networks, visual system, discrete cosine transform, visual image",
author = "Qingxiang Wu and McGinnity, {T. M.} and Liam Maguire and Arfan Ghani and Joan Condell",
year = "2009",
doi = "10.1007/978-3-642-04020-7_3",
language = "English",
isbn = "97836420402073",
pages = "21--29",
booktitle = "Emerging Intelligent Computing Technology and Applications",
publisher = "Springer Verlag",
address = "Austria",

}

TY - CHAP

T1 - Spiking neural network performs discrete cosine transform for visual images

AU - Wu, Qingxiang

AU - McGinnity, T. M.

AU - Maguire, Liam

AU - Ghani, Arfan

AU - Condell, Joan

PY - 2009

Y1 - 2009

N2 - The human visual system demonstrates powerful image processing functionalities. Inspired by the principles from neuroscience, a spiking neural network is proposed to perform the discrete cosine transform for visual images. The structure and the properties of the network are detailed in this paper. Simulation results show that the network is able to perform the discrete cosine transform for visual images. Based on this mechanism, the key features can be extracted in ON/OFF neuron arrays. These key features can be used to reconstruct the visual images. The network can be used to explain how the spiking neuron-based system can perform key feature extraction. The differences between the discrete cosine transform and the spiking neural network transform are discussed.

AB - The human visual system demonstrates powerful image processing functionalities. Inspired by the principles from neuroscience, a spiking neural network is proposed to perform the discrete cosine transform for visual images. The structure and the properties of the network are detailed in this paper. Simulation results show that the network is able to perform the discrete cosine transform for visual images. Based on this mechanism, the key features can be extracted in ON/OFF neuron arrays. These key features can be used to reconstruct the visual images. The network can be used to explain how the spiking neuron-based system can perform key feature extraction. The differences between the discrete cosine transform and the spiking neural network transform are discussed.

KW - spiking neural networks

KW - visual system

KW - discrete cosine transform

KW - visual image

U2 - 10.1007/978-3-642-04020-7_3

DO - 10.1007/978-3-642-04020-7_3

M3 - Chapter

SN - 97836420402073

SP - 21

EP - 29

BT - Emerging Intelligent Computing Technology and Applications

PB - Springer Verlag

ER -