基于神经网络的手写数字识别系统的设计与实现（本科）毕业设计论文.docVIP

中 南 大 学 本科生毕业论文（设计） 题 目 基于目 录 摘要 Ⅰ ABSTRACT Ⅱ 第一章 绪论 1 1.1手写体数字识别研究的发展及研究现状 1 1.2神经网络在手写体数字识别中的应用 2 1.3 论文结构简介 3 第二章 手写体数字识别 4 2.1手写体数字识别的一般方法及难点 4 2.2 图像预处理概述 5 2.3 图像预处理的处理步骤 5 2.3.1 图像的平滑去噪 5 2.3.2 二值话处理 6 2.3.3 归一化 7 2.3.4 细化 8 2.4 小结 9 第三章 特征提取 10 3.1 特征提取的概述 10 3.2 统计特征 10 3.3 结构特征 11 3.3.1 结构特征提取 11 3.3.2 笔划特征的提取 11 3.3.3 数字的特征向量说明 12 3.3 知识库的建立 12 第四章 神经网络在数字识别中的应用 14 4.1 神经网络简介及其工作原理 14 4.1.1神经网络概述[14] 14 4.1.2神经网络的工作原理 14 4.2神经网络的学习与训练[15] 15 4.3 BP神经网络 16 4.3.1 BP算法 16 4.3.2 BP网络的一般学习算法 16 4.3.3 BP网络的设计 18 4.4 BP学习算法的局限性与对策 20 4.5 对BP算法的改进 21 第五章 系统的实现与结果分析 23 5.1 软件开发平台 23 5.1.1 MATLAB简介 23 5.1.2 MATLAB的特点 23 5.1.3 使用MATLAB的优势 23 5.2 系统设计思路 24 5.3 系统流程图 24 5.4 MATLAB程序设计 24 5.5 实验数据及结果分析 26 结论 27 参考文献 28 致谢 30 附录 31 摘 要： ABSTRACT Handwritten character recognition is a very important and active research in pattern recognition. Theoretically, it is not an isolated technique. It concerns with the problem that all the other areas of pattern recognition must confronted; practically, being a kind of information processing measured, character recognition has a very broad application background and vast need of market. Thus, it is of both theoretical and practical significance. Artificial neural network recognition method is a new method of the research field in recent years, and this method has some merit that traditional technique do not have; good tolerance for error, strong sorting ability, strong parallel handling ability and strong self-learning ability as well as its off-line training and on-line recognizing. All these merits contribute its perfect performance in handling vast data set and handling in timely manner. It’s difficult to make accurate mathematics model for handwritten numeral recognition, so BP neural networks is used here. The key steps of neural networks pattern recognition are preprocessing and feature subset selection. In this paper, algorithm of feature subset selection basing on structural characteristics and statistical ch