手写体数字识别的软件设计(毕业设计论文)

毕业设计说明书手写体数字识别的软件设计学生姓名：学号：学院：专业：指导教师：2009年6月电子与计算机科学技术学院计算机科学与技术专业手写体数字识别的软件设计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强，且意义重大。本文主要的研究的工作集中在图像预处理和选择合适的特征向量，并实现一个完整手写体数字识别系统。本文中对几种常见的二值化算法进行比较，并最终选择基于梯度的二值化算法；在本文中，提出了一种方法来解决结构点检测的传统方法的缺陷。另外本文还提出将一般用来直接识别字符的凸凹特征作为字符的特征向量之一。通过对NIST的数据进行测试，实验数据表明本文设计的数字识别系统对手写体数字识别具有较高的识别率。关键词：手写体数字识别，特征向量，二值化算法，凸凹特征TheSoftwareDesignofHandwrittenNumeralRecognitionAbstractThehandwrittennumeralrecognitionisatechnology,whichautorecognizesthehandwritingArabiannumeralviamachinesorcomputers,andaspecialfieldintheOpticalCharacterRecognitiontechnology.Thenhandwrittennumeralrecognitionresearchisgreatlygeneral-purposeandsignificative,becauseoftheuniversalArabicnumerals.Onthesamescore,thehandwrittennumeral,recognitiontechnologiesareplayinganimportantroleinanumberofautomatizationsystems.Inthispaper,themainstudyfocusedonimagepre-processingandselectionofappropriatefeaturevectors,andtorealizeacompletesystemofhandwrittennumeralrecognition.Thereareseveralcommoncomparisonsofbinarizationalgorithminthisarticle,andchoosethegradient-basedbinarizationalgorithmfinally;andobjectingtothedefectionoftraditionalmethodsofstructuralpointdetection,asolutiontotheproblemwasputupinthisarticle.Inaddition,thispaperalsoraisestheconvex-concavefeatureasoneofthecharacterfeaturevectors.ThroughtheNISTtestdata,experimentaldatashowsthatthedigitalidentificationsystemdesignedforhandwrittennumeralrecognitionhasahighrecognitionrate.Keywords:Handwrittennumeralrecognition,Characterfeaturevectors,Binarizationalgorithm,Convex-concavefeature中北大学2009届毕业设计说明书第Ⅰ页共Ⅱ页目录1绪论......................................................................................................................................11.1字符识别概述...................................................................................................................11.2手写数字识别的意义和应用前景...................................................................................21.3字符识别的研究与发展...................................................................................................31.4手写数字识别的难点.......................................................................................................31.5国内外研究现状...............................................................................................................41.6手写体数字识别系统概述...............................................................................................51.7本文内容安排...................................................................................................................62手写体数字识别中预处理技术..........................................................................................82.1平滑去噪...........................................................................................................................82.2二值化.............................................................................................................................102.3归一化.............................................................................................................................162.4倾斜校正.........................................................................................................................202.5细化.................................................................................................................................223手写体数字识别中串切分技术........................................................................................253.1切分方法概述.................................................................................................................253.2手写数字串常用方法简介.............................................................................................253.2.1投影法的直线切分......................................................................................................253.2.2滴水算法......................................................................................................................263.2.3动态规划算法..............................................................................................................263.2.4滑动窗口法..................................................................................................................263.2.5多模具切分法..............................................................................................................263.3本文手写数字串切分方法介绍.....................................................................................274手写体数字识别中特征值提取技术................................................................................294.1特征提取概述.................................................................................................................294.2手写体字符特征提取方法概述.....................................................................................304.3手写体数字识别中的结构特征提取.............................................................................324.3.1结构点特征..................................................................................................................32中北大学2009届毕业设计说明书第Ⅱ页共Ⅱ页4.3.2穿越密度特征.........