HMM在脱机手写数字识别中的应用设计论文.pdf

HMM 在脱机手写数字识别中的应用 数学与应用数学专业 许文超(099084099) 指导老师：汪忠志 教授 摘要 手写体数字识别是利用机器或计算机自动辨认手写体阿拉伯数字的一种技 术，是光学字符识别技术的一个分支。由于阿拉伯数字的世界通用性，并且数字 的识别和处理也常常是一些自动化系统的核心和关键，所以对手写体数字识别研 究通用性意义重大。 本文主要用隐Markov 模型(HMM)来研究脱机手写数字识别，由于HMM 在 语音识别上的成功应用，所以人们把它应用到了手写体识别上。本文的内容总体 上可分为三个部分，第一个部分是介绍HMM 的基本理论，主要是HMM 中的三 大问题以及对应的三大算法；第二部分是介绍数字图片的预处理和特征提取，这 部分属于图像处理方向，并且在手写体数字识别中很重要，特别是提取一个稳定 而有效的特征决定着识别是否成功；第三部分是具体地实现这一识别过程，并且 用Matlab 实现了一个脱机手写数字识别系统。 关键词：隐Markov 模型；手写体数字识别；三大算法；预处理；特征提取 1 Abstract The handwritten numeral recognition is a technology, which auto recognizes the handwriting Arabian numeral via machines or computers, and a special field in the Optical Character Recognition technology. Then handwritten numeral recognition research is greatly general-purpose and significative, because of the universal Arabic numerals. On the same score, the handwritten numeral, recognition technologies are playing an important role in a number of automatization systems. In this paper, we use hidden Markov models(HMM) to study the off-line handwritten numeral recognition, because of HMMs successful application in speech recognition, people apply it to the handwriting recognition. This paper can generally be divided into three parts, the first part introduces the basic theory of HMM, and the important is three major issues of HMM and the corresponding three algorithms; The second part introduces the digital image preprocessing and feature extraction, this part belongs to image processing, and it is very important in the handwriting recognition, especially extracting a stable and effective feature determines whether the successful recognition; The third part implements recognition process, and we use Matlab to obtain an off-line hand