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

Zhan Shi*, Jinglu Hu

*この研究の対応する著者

研究成果: Conference contribution

4 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトルProceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10
ページ330-335
ページ数6
DOI
出版ステータスPublished - 2010 12月 1
イベント2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10 - Cairo, Egypt
継続期間: 2010 11月 292010 12月 1

出版物シリーズ

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

Conference

Conference2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10
国/地域Egypt
CityCairo
Period10/11/2910/12/1

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ サイエンスの応用
  • ハードウェアとアーキテクチャ

フィンガープリント

「Image edge detection method based on A simplified PCNN model with anisotropic linking mechanism」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル