Zhou Fuqiang

A Real Time Fingerprint Recognition System Based On Novel Fingerprint Matching Strategy

Fingerprint based personal identification is becoming more and more popular in everyday life. Designing an accurate real time automatic fingerprint identification system is of great importance in many circumstances, and this question has attracted lot of scholars attention. In this paper we present a new real time fingerprint recognition system based on a novel fingerprint minutiae matching algorithm. The system is developed to be applicable to todays embedded systems for fingerprint authentication, in which small area sensors are employed. The system is comprised of fingerprint enhancement and quality control, fingerprint feature extraction, fingerprint matching using a novel matching algorithm, and connection with other identification system. Experiment on FVC2002 database show this system is fast, accurate and suitable for the real time personal identification.

INFLUENCE FACTORS OF ROLLING FORCE IN TANDEM COLD ROLLING

The laws of influence factors of rolling factors are studied by dividing the rolling deformation into micro elements. Based on the plastic deformation equation of the micro element, the model of the normal rolling stress is put forward.Based on the artificial neural networks corrected coefficient and refere- nce working points,the mathematic models of the deformation resistance of the strip and the friction coefficient are developed by thinking about the nonlinear factors,and the laws of influe- nce factors,such as the deformation resistance and friction coeffients which are analyzed in the rolling deformation.The iterative model for calculation by computer is also built to solve the coupling problem between the flatten radius of the working roll and the rolling force.The calculating precision of the rolling force is high verified by the field data of the industrial mill,and the models can be applied to the production practice.

The differential approximation method to determine a scale parameter interval for a multi-scale Gaussian kernel RVM regression

A scale parameter of a Gaussian kernel relevance vector machine (RVM) directly determine a result of the RVM regression. Because this scale parameter interval is from zero to positive infinite, it is difficult to choose the proper scale parameter for the Gaussian kernel function. This paper introduces a differential approximation method (DAM) to determine a scale parameter interval for a Gaussian kernel function. We acquired a very small scale parameter interval by utilizing the DAM from a training set. After training the multi-scale Gaussian kernel RVM, we easily searched the proper scale parameter values for Gaussian kernels in the scale parameter interval by a simple search algorithm. The results of experiments indicate the DAM can determine the proper scale parameter interval. The result of RVM predictor in the test set is very excellent.