Title :
Two Theorems on the Robust Designs for Dilation and Erosion CNNs
Author :
Jian, Shu ; Zhao, Bing ; Min, Lequan
Author_Institution :
Univ. of Sci. & Technol. Beijing, Beijing
Abstract :
The cellular neural/nonlinear network (CNN) has become a new tool for image and signal processing, robotic and biological visions, and higher brain functions. Based our previous research, this paper set up two new theorems of robust designs for Dilation and Erosion CNNs processing gray-scale images, which provide parameter inequalities to determine parameter intervals for implementing prescribed image processing functions, respectively. Four numerical simulation examples for Dilation and Erosion CNNs are given to illustrate the effectiveness of our theorems.
Keywords :
cellular neural nets; image processing; biological vision; cellular neural/nonlinear network; dilation CNN; gray-scale image; parameter inequality; signal processing; Biology; Biomedical signal processing; Cellular networks; Cellular neural networks; Gray-scale; Image edge detection; Numerical simulation; Robot vision systems; Robustness; Signal design;
Conference_Titel :
Communications, Circuits and Systems, 2007. ICCCAS 2007. International Conference on
Conference_Location :
Kokura
Print_ISBN :
978-1-4244-1473-4
DOI :
10.1109/ICCCAS.2007.4348189
