A Survey on Image Enhancement Techniques: Classical Spatial Filter, Neural Network, Cellular Neural Network, and Fuzzy Filter

2006 ◽  
Author(s):  
D. H. Rao ◽  
Patavardhan Prashant Panduranga
Keyword(s):  
Neural Network ◽  
Image Enhancement ◽  
Cellular Neural Network ◽  
Spatial Filter ◽  
Fuzzy Filter

scholarly journals Biomimetic adaptive memristive cellular neural network for image enhancement

2020 ◽  
Vol 50 (12) ◽  
pp. 1850
Author(s):  
Xiaofang HU ◽  
Shukai DUAN ◽  
Yue ZHOU ◽  
Li LUO ◽  
Yawen ZHENG
Keyword(s):  
Neural Network ◽  
Image Enhancement ◽  
Cellular Neural Network

Optimizing Time-multiplexing Raster Cellular Neural Network simulator using genetic algorithms with RK8(6)

2011 ◽  
Vol 3 (6) ◽  
pp. 87-90
Author(s):  
O. H. Abdelwahed O. H. Abdelwahed ◽  
◽  
M. El-Sayed Wahed ◽  
O. Mohamed Eldaken
Keyword(s):  
Neural Network ◽  
Genetic Algorithms ◽  
Cellular Neural Network ◽  
Network Simulator

Cellular Neural Network Based on Hybrid Linear Matrix Inequality and Particle Swarm Optimization for Noise Removal of Color Image

2011 ◽  
Vol 422 ◽  
pp. 771-774
Author(s):  
Te Jen Su ◽  
Jui Chuan Cheng ◽  
Yu Jen Lin
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Linear Matrix Inequality ◽  
Color Image ◽  
Particle Swarm ◽  
Cellular Neural Network ◽  
Noise Removal ◽  
Linear Matrix ◽  
Matrix Inequality ◽  
Swarm Optimization

This paper presents a color image noise removal technique that employs a cellular neural network (CNN) based on hybrid linear matrix inequality (LMI) and particle swarm optimization (PSO). For designing templates of CNN, the Lyapunov stability theorem is applied to derive the criterion for the uniqueness and global asymptotic stability of the CNN’s equilibrium point. The template design is characterized as a standard LMI problem, and the parameters of templates are optimized by PSO. The input templates are obtained by employing the CNN’s property of saturation nonlinearity, which can be used to eliminate noise from arbitrary corrupted images. The demonstrated examples are compared favorably with other available methods, which illustrate the better performance of the proposed LMI-PSO-CNN methodology.

Sigma–delta cellular neural network for 2D modulation

2008 ◽  
Vol 21 (2-3) ◽  
pp. 349-357 ◽  
Author(s):  
Hisashi Aomori ◽  
Tsuyoshi Otake ◽  
Nobuaki Takahashi ◽  
Mamoru Tanaka
Keyword(s):  
Neural Network ◽  
Cellular Neural Network ◽  
Sigma Delta
Sign in / Sign up

Export Citation Format

Share Document