Rotation Invariant Detection of Moving and Standing Objects Using Analogic Cellular Neural Network Algorithms Based on Ring-Codes
スポンサーリンク
概要
- 論文の詳細を見る
Cellular Neural Networks (CNNs) are nonlinear dynamic array processors with mainly local interconnections. In most of the applications, the local interconnection pattern, called cloning template, is translation invariant. In this paper, an optimal ring-coding method for rotation invariant description of given set of objects, is introduced. The design methodology of the templates based on the ring-codes and the synthesis of CNN analogic algorithms to detect standing and moving objects in a rotationally invariant way, is discussed in detail. It is shown that the algorithms can be implemented using the CNN Universal Machine, the recently invented analogic visual microprocessor. The estimated time performance and the parallel detecting capability is emphasized, the limitations are also thoroughly investigated.
- 社団法人電子情報通信学会の論文
- 1995-10-25
著者
-
USHIDA Akio
Department of Mechanical and Electronic Engineering, Tokushima Bunri University
-
Ushida Akio
Department Of Electrical And Electronic Engineering The University Of Tokushima
-
Ushida Akio
Department Of Electrical And Electronic Engineering Faculty Of Engineering Tokushima University
-
REKECZKY Csaba
Analogical and Neural Computing Systems Laboratory, Computer and Automation Institute
-
Ushida Akio
Department Of Mechanical And Electronic Engineering Faculty Of Engineering Tokushima Bunri Universit
-
Roska T
Computer And Automation Institute Hungarian Academy Of Sciences
-
Rekeczky Csaba
Computer And Automation Institute Hungarian Academy Of Sciences Hungary
-
Roska Tamas
Analogical and Neural Computing Laboratory, Computer and Automation Institute, Hungarian Academy of
関連論文
- Fast Simulation Technique of Plane Circuits via Two-Layer CNN-Based Modeling
- Spice-Oriented Frequency-Domain Analysis of Nonlinear Electronic Circuits(Analog Circuit Techniques and Related Topics)
- A Reduction Technique for RLCG Interconnects Using Least Squares Method(Analog Circuit Techniques and Related Topics)
- A Modeling Technique of Interconnects Using Numerical Laplace Transformation
- Efficient Curve Fitting Technique for Analysis of Interconnect Networks with Frequency-Dpendent Parameteters (Section on VLSI Design and CAD Algorithms)
- A Spectral Method for Transient Analysis of Nonlinear Transmission Line Using Line Partitioning Technique
- Analysis of Nonuniform Transmission Lines Using Chebyshev Expansion Method and Moment Techniques (Special Section on VLSI Design and CAD Algorithms)
- Analysis of Two Dimensional Circuits Based on Multi-Conductor Theorem
- Analysis of Nonuniform and Nonlinear Transmission Lines via Frequency-Domain Technique
- Analysis of Reactance Oscillators Having Multi-Mode Oscillations (Circuit Theory)
- Phase-Inversion Waves in Oscillators Coupled by Two Kinds of Inductors as a Ladder(Nonlinear Theory and its Applications)
- Analysis of Phase-Inversion Waves in Coupled Oscillators Synchronizing at In-and-Anti-Phase(Noliner Problems)
- Phase-Waves in a Ladder of Oscillators
- Synchronization and Its Analysis in Chaotic Systems Coupled by Transmission Line
- Steady-State Response of Nonlinear Circuits Containing Parasitic Elements (Special Section of Papers Selected from ITC-CSCC'99)
- BER Estimation of a Chaos Communication System including Modulation-Demodulation Circuits
- Wave Propagation Phenomena of Phase States in Oscillators Coupled by Inductors as a Ladder
- Performance Comparison of Communication Systems Using Chaos Synchronization
- On the Influence of Transmission Line on Communication System Using Chaos Synchronization
- Analysis of Bifurcation Phenomena on Two Chaotic Circuits Coupled by an Inductor
- Detecting Lung Cancer Symptoms with Analogic CNN Algorithms Based on a Constrained Diffusion Template
- Feature Extraction of Postage Stamps Using an Iterative Approach of CNN
- Generation of Various Types of Spatio-Temporal Phenomena in Two-Layer Cellular Neural Networks(Nonlinear Problems)
- Image Processing of Two-Layer CNNs : Applications and Their Stability(Nonlinear Theory and Its Applications)
- Sensitivity Analysis and Optimization Algorithm : Based on Nonlinear Programming
- Fast Simulation Technique of Plane Circuits via Two-Layer CNN-Based Modeling
- Circuit Realization of a Coupled Chaotic Circuits Network and Irregular Pattern Switching Phenomenon (Special Section on Nonlinear Theory and Its Applications)
- Synchronization Phenomena in Resistively Coupled Oscillators with Different Frequencies (Special Section on Nonlinear Theory and its Applications)
- On a Ring of Oscillators Sharing Inductors
- Adaptive Simulated Annealing in CNN Template Learning
- Cnn Template Learning Using Adaptive Simulated Annealing-Performance Comparison with a Genetic Algorithm
- Error Spectrum Shaping in 2-D State-Space Digtal Filters Using Error Diagonal Feedback
- Markov Chain Modeling of Intermittency Chaos and Its Application to Hopfleld NN(Selected Papers from the 16th Workshop on Circuits and Systems in Karuizawa)
- Transient Analysis of Nonlinear Transmission Lines by Hybrid Harmonic Balance Method(Numerical Ordinary Differential Equations and Related Topics)
- Rotation Invariant Detection of Moving and Standing Objects Using Analogic Cellular Neural Network Algorithms Based on Ring-Codes
- Spice-Oriented Algorithm for Peak Search and Stability Assessment for Frequency Response (特集 非線形電子回路)