Robust Designs for Directed Edge Overstriking CNNs with Applications

  • Authors:
  • Yongmei Su;Lequan Min;Xinjian Zhuo

  • Affiliations:
  • Applied Science School, University of Science and Technology Beijing, Beijing, PR China 100083;Applied Science School, University of Science and Technology Beijing, Beijing, PR China 100083;School of Information Engineering, University of Post and Telecommunications, Beijing, PR China 100083

  • Venue:
  • ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

A kind of templates of coupled Cellular Neural Network (CNN) are introduced, which are able to generate gray edges to a binary image and overstrike them "directionally". The robustness analysis gives the template parameter inequalities which guarantee the corresponding CNNs to work well for performing prescribed tasks. As applications, the CNNs may be used to generate art letters.