Image edge detection method based on A simplified PCNN model with anisotropic linking mechanism

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper presents a novel image edge detection method based on a simplified pulse coupled neural network with anisotropic interconnections (PCNNAI) by applying an anisotropic linking mechanism. PCNNAI utilizes the anisotropic linking mechanism to create an adaptive synaptic weight matrix to achieve the anisotropic interconnection model among neurons. Therefore, the neurons corresponding to edge and non-edge pixels will receive different feedback signal from neighborhood. Due to the PCNN structure the edges will be detected by different internal activity of edge neurons and non-edge neurons. Comparing with conventional PCNN edge detection methods, PCNNAI simplifies the system structure and the outputs are controllable, meanwhile PCNNAI also achieves more accurate results than the classical image edge detectors. Experimental results show that PCNNAI is effective at image edge detection.

Original languageEnglish
Title of host publicationProceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10
Pages330-335
Number of pages6
DOIs
Publication statusPublished - 2010
Event2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10 - Cairo
Duration: 2010 Nov 292010 Dec 1

Other

Other2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10
CityCairo
Period10/11/2910/12/1

Fingerprint

Edge detection
Neurons
Neural networks
Pixels
Detectors
Feedback

Keywords

  • Anisotropic linking mechanism
  • Edge detection
  • Pulse coupled neural network

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Hardware and Architecture

Cite this

Shi, Z., & Furuzuki, T. (2010). Image edge detection method based on A simplified PCNN model with anisotropic linking mechanism. In Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10 (pp. 330-335). [5687242] https://doi.org/10.1109/ISDA.2010.5687242

Image edge detection method based on A simplified PCNN model with anisotropic linking mechanism. / Shi, Zhan; Furuzuki, Takayuki.

Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10. 2010. p. 330-335 5687242.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shi, Z & Furuzuki, T 2010, Image edge detection method based on A simplified PCNN model with anisotropic linking mechanism. in Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10., 5687242, pp. 330-335, 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10, Cairo, 10/11/29. https://doi.org/10.1109/ISDA.2010.5687242
Shi Z, Furuzuki T. Image edge detection method based on A simplified PCNN model with anisotropic linking mechanism. In Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10. 2010. p. 330-335. 5687242 https://doi.org/10.1109/ISDA.2010.5687242
Shi, Zhan ; Furuzuki, Takayuki. / Image edge detection method based on A simplified PCNN model with anisotropic linking mechanism. Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10. 2010. pp. 330-335
@inproceedings{573096a881674fefbc49b8883d83653c,
title = "Image edge detection method based on A simplified PCNN model with anisotropic linking mechanism",
abstract = "This paper presents a novel image edge detection method based on a simplified pulse coupled neural network with anisotropic interconnections (PCNNAI) by applying an anisotropic linking mechanism. PCNNAI utilizes the anisotropic linking mechanism to create an adaptive synaptic weight matrix to achieve the anisotropic interconnection model among neurons. Therefore, the neurons corresponding to edge and non-edge pixels will receive different feedback signal from neighborhood. Due to the PCNN structure the edges will be detected by different internal activity of edge neurons and non-edge neurons. Comparing with conventional PCNN edge detection methods, PCNNAI simplifies the system structure and the outputs are controllable, meanwhile PCNNAI also achieves more accurate results than the classical image edge detectors. Experimental results show that PCNNAI is effective at image edge detection.",
keywords = "Anisotropic linking mechanism, Edge detection, Pulse coupled neural network",
author = "Zhan Shi and Takayuki Furuzuki",
year = "2010",
doi = "10.1109/ISDA.2010.5687242",
language = "English",
isbn = "9781424481354",
pages = "330--335",
booktitle = "Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10",

}

TY - GEN

T1 - Image edge detection method based on A simplified PCNN model with anisotropic linking mechanism

AU - Shi, Zhan

AU - Furuzuki, Takayuki

PY - 2010

Y1 - 2010

N2 - This paper presents a novel image edge detection method based on a simplified pulse coupled neural network with anisotropic interconnections (PCNNAI) by applying an anisotropic linking mechanism. PCNNAI utilizes the anisotropic linking mechanism to create an adaptive synaptic weight matrix to achieve the anisotropic interconnection model among neurons. Therefore, the neurons corresponding to edge and non-edge pixels will receive different feedback signal from neighborhood. Due to the PCNN structure the edges will be detected by different internal activity of edge neurons and non-edge neurons. Comparing with conventional PCNN edge detection methods, PCNNAI simplifies the system structure and the outputs are controllable, meanwhile PCNNAI also achieves more accurate results than the classical image edge detectors. Experimental results show that PCNNAI is effective at image edge detection.

AB - This paper presents a novel image edge detection method based on a simplified pulse coupled neural network with anisotropic interconnections (PCNNAI) by applying an anisotropic linking mechanism. PCNNAI utilizes the anisotropic linking mechanism to create an adaptive synaptic weight matrix to achieve the anisotropic interconnection model among neurons. Therefore, the neurons corresponding to edge and non-edge pixels will receive different feedback signal from neighborhood. Due to the PCNN structure the edges will be detected by different internal activity of edge neurons and non-edge neurons. Comparing with conventional PCNN edge detection methods, PCNNAI simplifies the system structure and the outputs are controllable, meanwhile PCNNAI also achieves more accurate results than the classical image edge detectors. Experimental results show that PCNNAI is effective at image edge detection.

KW - Anisotropic linking mechanism

KW - Edge detection

KW - Pulse coupled neural network

UR - http://www.scopus.com/inward/record.url?scp=79851486797&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79851486797&partnerID=8YFLogxK

U2 - 10.1109/ISDA.2010.5687242

DO - 10.1109/ISDA.2010.5687242

M3 - Conference contribution

AN - SCOPUS:79851486797

SN - 9781424481354

SP - 330

EP - 335

BT - Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10

ER -