Corpus ID: 18059558

Sine-Cosine-Taylor-Like Method for Hole-Filler ICNN Simulation

@inproceedings{Senthilkumar2011SineCosineTaylorLikeMF,
  title={Sine-Cosine-Taylor-Like Method for Hole-Filler ICNN Simulation},
  author={S. Senthilkumar and A. Rahni and M. Piah},
  year={2011}
}
Sine-Cosine-Taylor-Like method is employed to improve the performance of image or handwritten character recognition under improved cellular non-linear network environment. The ultimate aim of this paper is focused on developing an efficient design strategy for simulating hole filler under ICNN arrays with a set of inequalities satisfying its output characteristics by considering the parameter range. 
1 Citations

Figures from this paper

Employing Different Types of Taylor-Like Methods for Image Processing and Initial Value Problems
TLDR
Sine-Cosine- Taylor like, Cosine Taylor like and Explicit Taylor like methods are used to solve image processing and initial value problems and the results disclose the effectiveness of adapted approaches to solve the considered problems. Expand

References

SHOWING 1-10 OF 35 REFERENCES
An Efficient Numerical Integration Algorithm for Cellular Neural Network Based Hole-Filler Template Design
TLDR
A design method for the template of the hole-filler used to improve the performance of the character recognition using Numerical integration algorithms. Expand
CNN Based Hole Filler Template Design Using Numerical Integration Techniques
TLDR
A design method for the template of a hole-filler used to improve the handwritten character recognition using numerical integration algorithms, based on the dynamic analysis of a cellular neural network (CNN). Expand
CNN cloning template: hole-filler
A CNN (cellular neural network) template for hole-filling is reported. There are many holes in Japanese characters and the CNN described can be used in addition to a connected-component-detector CNNExpand
An analytic method for designing simple cellular neural networks
A method is proposed for synthesizing cellular neural networks (CNNs) designed for simple applications. Based on the comparison principle for ordinary differential equations, this method leads to aExpand
A COMPARISON OF RK-FOURTH ORDERS OF VARIETY OF MEANS AND EMBEDDED MEANS ON MULTILAYER RASTER CNN SIMULATION
In this paper an adaptable algorithm for simulating CNN arrays is implemented using various RK-fourth order means such as Arithmetic Mean [AM], Centroidal Mean [CM], Harmonic Mean [HM], ContraExpand
Implementation of time-multiplexed CNN building block cell
  • K. K. Lai, P. Leong
  • Computer Science
  • Proceedings of Fifth International Conference on Microelectronics for Neural Networks
  • 1996
TLDR
The underlying theory, method, and the circuit architecture of a VLSI implementation of a cellular neural network by using the time-multiplexed method is described. Expand
An New Automatic Nucleated Cell Counting Method With Improved Cellular Neural Networks (ICNN)
TLDR
A new automatic nucleated cell counting method based on improve cellular neural networks (ICNN) is proposed, which improves the CNN output function and practically design all the templates, then proves the stability. Expand
Cellular neural networks
  • L. Chua, L. Yang
  • Computer Science
  • 1988., IEEE International Symposium on Circuits and Systems
  • 1988
TLDR
Examples of cellular neural networks which can be designed to recognize the key features of Chinese characters are presented and some theorems concerning the dynamic range and the steady states of Cellular neural networks are proved. Expand
Cellular neural networks: Theory and circuit design
TLDR
An abstract normalized definition of cellular neural networks with arbitrary interconnection topology is given and the property of convergence is found to be of central importance: large classes of convergent CNNs in practice always asymptotically approach some stable equilibrium where each component of the corresponding output is binary-valued. Expand
Cellular neural networks: theory
A novel class of information-processing systems called cellular neural networks is proposed. Like neural networks, they are large-scale nonlinear analog circuits that process signals in real time.Expand
...
1
2
3
4
...