Robust Designs for Templates of Directional Extraction Cellular Neural Network with Application

The cellular neural/nonlinear network (CNN) is a powerful tool for image and video signal processing, robotic and biological visions. In this paper, the selected objects extraction (SOE) CNN was generated to directional extraction (DE) CNN which enhance the capabilities of CNNs and improve their efficiency. Based on analytical approach, a theorem of designing robust templates for DE CNNs was established, which provides parameter inequalities to determine parameter intervals for implementing the corresponding functions. Several examples are provided to illustrate the effectiveness of the theorem for extracting selected objects directionally in binary images.

[1]  Eugenio Di Sciascio,et al.  A CNN-based object-oriented coding system for real-time video compression , 2004, IEEE 6th Workshop on Multimedia Signal Processing, 2004..

[2]  Lequan Min,et al.  Design for robustness edgegray detection CNN , 2004, 2004 International Conference on Communications, Circuits and Systems (IEEE Cat. No.04EX914).

[3]  M. Namba,et al.  The design of cellular neural networks for associative memory with multiple memory tables , 2005, 2005 9th International Workshop on Cellular Neural Networks and Their Applications.

[4]  LIUJin-Zhu,et al.  Design for CNN Templates with Performance of Global Connectivity Detection , 2004 .

[5]  Min Lequan,et al.  Robustness Design for CNN Templates with Performance of Extracting Closed Domain , 2006 .

[6]  Leon O. Chua,et al.  Cellular Neural Networks and Visual Computing , 2002 .

[7]  Giovanni Egidio Pazienza,et al.  Robot vision with cellular neural networks: a practical implementation of new algorithms , 2007, Int. J. Circuit Theory Appl..

[8]  Tamás Szirányi,et al.  Texture recognition using a superfast cellular neural network VLSI chip in a real experimental environment , 1997, Pattern Recognit. Lett..

[9]  Leon O. Chua,et al.  CNN: A Vision of Complexity , 1997 .

[10]  Lequan Min.  Robustness designs of a kind of uncoupled CNNs with applications , 2005, 2005 9th International Workshop on Cellular Neural Networks and Their Applications.

[11]  István Petrás,et al.  Receptive Field Atlas and Related CNN Models , 2004, Int. J. Bifurc. Chaos.

[12]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[13]  Lequan Min,et al.  Robust Designs for Gray-Scale Global Connectivity Detection CNN Templates , 2007, Int. J. Bifurc. Chaos.

[14]  Yih-Lon Lin,et al.  Robust Template Decomposition with Restricted Weights for Cellular Neural Networks Implementing an Arbitrary Boolean Function , 2007, Int. J. Bifurc. Chaos.

[15]  George S. Moschytz,et al.  An exact and direct analytical method for the design of optimally robust CNN templates , 1999 .