图像特征识别方法研究

图像特征识别的方法及其技术实现系当前模式识别研究领域中最为热门的研究课题之一。本文针对NMI(归一化转动惯量)特征识别、不变矩特征识别和比例特征识别三种图像特征识别方法．通过实验分析了该三种识别方法的缩放不变性、旋转不变性、平移不变性以及不同物体之间的特征差异。实验数据显示NMI特征识别方法具有最佳的识别效果和最快的处理速度。     

An Intrusion Detection System based on evidence theory and Rough Set Theory

In this paper, we propose a novel Intrusion Detection System (IDS) architecture utilizing both the evidence theory and Rough Set Theory (RST). Evidence theory is an effective tool in dealing with un-certainty question. It relies on the expert knowledge to provide evidences, needing the evidences to be inde-pendent, and this make it difficult in application. To solve this problem, a hybrid system of rough sets and evidence theory is proposed. Firstly, simplification are made based on Variable Precision Rough Set (VPRS) conditional entropy. Thus, the Basic Belief Assignment (BBA) for all evidences can be calculated. Secondly, Dempster’s rule of combination is used, and a decision-making is given. In the proposed approach, the diffi-culties in acquiring the BBAs are solved, the correlativity among the evidences is reduced and the subjectiv-ity of evidences is weakened. An illustrative example in an intrusion detection shows that the two theories combination is feasible and effective.