【摘要】 该文提出了一种基于支撑向量机的支票手写体数字识别系统。支撑向量机方法,由于建立在结构风险最小化的基础上,而不仅仅使经验风险达到最小,从而突破了传统模式识别方法的局限,使得基于支撑向量机的分类器具有较好的推广能力。文中重点阐述了支撑向量机的基本原理和集成在该系统中的重要的处理模块,实验结果表明该系统具有较高的识别率和较强的实用性。更多还原

【Abstract】 A new recognition system of handwritten numerals on checks using support vector machine is presented in this paper.Support vector machine(SVM)operates on the principle of structure risk minimization instead of traditional pattern recognition methods that only keep the empirical risk minimization;hence a better generalization ability is guaranteed.In this paper,the problems to solve the theory of applying SVM in recognition system of handwritten numerals on checks and several processing modules,which have been integrated in the system,are addressed,and the system is proved to be practical with the experimental results.更多还原