Search

Fingerprint Recognition Technologies are becoming more popular to be used as a representative of biometrics nowadays. As all electronics devices tends to be smaller and smaller, people pays more attention to "linear sensor" method. The most important factor for securing the reliable Fingerprint Recognition Technology is pursuing the enhancement of the captured fingerprint image from sensors. This paper presents an algorithm that uses Image Estimation and Reconstruction Method in order to embody precisely the image captured from Linear Sensors. The proposed algorithm is verified theoretically and experimentally that the image can be perfectly reconstructed from the fingerprint on the linear sensor even though the finger position is displaced vertically, horizontally, and/or rotationally. Also this system demonstrates much higher recognition and authentication rates than any other existing systems. [ABSTRACT FROM AUTHOR]

This paper proposes a new ouput-feedback adaptive fuzzy controller for SISO affine nonlinear systems. The previous output-feedback control algorithms are all based on the state observer (e.g., higher-order-observer) or additional low-pass filter to make the estimation error dynamics SPR, which makes the stability analysis of the closed-loop system and real implementation very complicated. The distingushied aspect of the proposed output-feedback control algorithm is that no state observer or low-pass filter is employed. Only the output error is used to generate control input and update laws for unknown fuzzy parameters. The stability analysis depends heavily on the universal function approximation property of the fuzzy system to estimate unknown function of the desired control input. It is shown that, combining this simple output-feedback control algorithm with an online self-structuring fuzzy system, the Lyapunov stability of the closed-loop system is globally guarnateed. [ABSTRACT FROM AUTHOR]

Modeling of nonlinear static system using neural network based intelligent technology is presented in this paper. The architecture of the intelligent system is combined neural network with polynomial neural network. The composite architecture is designed to get a heuristic approximation method for nonlinear static system modeling. Owing to the approximation capabilities, neural networks have been widely utilized to process modeling, whereas the polynomial neural network is an analysis technique for identifying nonlinear relationships between inputs and outputs of the target system. So the hybrid architecture can harmonize the advantages of the each modeling methodology. Simulation results of the intelligent technology will be shown efficient and good performance. [ABSTRACT FROM AUTHOR]