Automatic authentication using rough set-based technique and fuzzy decision  

作　　者：陈宁 冯博琴 王海笑 张浩 

机构地区：[1]College of Computer Science,Xi'an Polytechnic University [2]Computer Teching and Experiment Center,Xi'an Jiaotong University [3]29 Bayowski Road West Orange [4]Shenzhen Traffic Control Center

出　　处：《Journal of Harbin Institute of Technology(New Series)》2009年第2期247-250,共4页哈尔滨工业大学学报（英文版）

基　　金：Sponsored by the National High Technology Research and Development Program of China (Grant No. 2003AA1Z2610)

摘　　要：This study introduced an automatic authentication technique for checking the genuineness of a vehicle. The rough set-based technique was used to handle the uncertainty arisen from artifacts in the acquired images imprinted on a vehicle. However, it has been proved to be NP-hard to find all reductions and the minimal reduction, and generally different heuristic algorithms were used to find a set of reductions and the Ganssian distribution was used to describe the uncertainty to achieve the minimal reduction. On the basis of inductive logic programming, the technique can distinguish between two similar images, as is superior to the conventional pattern-recognition technique being merely capable of classifier. Furthermore, it can avoid some failures of the technique based on the correlation coefficient to authenticate binary image. The experiments show an accuracy rate close to 93. 2%.This study introduced an automatic authentication technique for checking the genuineness of a vehicle.The rough set-based technique was used to handle the uncertainty arisen from artifacts in the acquired images imprinted on a vehicle.However,it has been proved to be NP-hard to find all reductions and the minimal reduction,and generally different heuristic algorithms were used to find a set of reductions and the Gaussian distribution was used to describe the uncertainty to achieve the minimal reduction.On the basis of inductive logic programming,the technique can distinguish between two similar images,as is superior to the conventional pattern-recognition technique being merely capable of classifier.Furthermore,it can avoid some failures of the technique based on the correlation coefficient to authenticate binary image.The experiments show an accuracy rate close to 93.2%.

关 键 词：E-GOVERNMENT UNCERTAINTY automatic authentication rough set 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论] TG519.1[自动化与计算机技术—计算机科学与技术]