【正文】 濟(jì)南大學(xué)泉城學(xué)院 畢 業(yè) 論 文 題 目 基于 BP 神經(jīng)網(wǎng)絡(luò)的字母識(shí)別系統(tǒng) 設(shè)計(jì)與實(shí)現(xiàn) 專(zhuān) 業(yè) 電氣工程及其自動(dòng)化 班 級(jí) 07Q2 學(xué) 生 學(xué) 號(hào) 指導(dǎo)教師 二〇一一 年六月七日 濟(jì)南大學(xué)泉城學(xué)院畢業(yè)論文 I 摘 要 基于前向反饋神經(jīng)網(wǎng)絡(luò)的字母識(shí)別技術(shù)在科學(xué)技術(shù)日新月異的今天迅速得到發(fā)展，在諸多的方面得到應(yīng)用包括出版、金融、軍事、現(xiàn)金登記 、頁(yè)面瀏覽以及任何帶有重復(fù)性、變化性數(shù)據(jù)的文件 。 英文字母識(shí)別系統(tǒng)的設(shè)計(jì)經(jīng)過(guò)以下幾個(gè)過(guò)程：預(yù)處理、特征提取、 BP 神經(jīng)網(wǎng)絡(luò)的訓(xùn)練、識(shí)別。本文的重點(diǎn)在于 BP 神經(jīng)網(wǎng)絡(luò)。 本文運(yùn)用的是三層神經(jīng)網(wǎng)絡(luò)，輸入層、隱含層、輸出層。隱含層節(jié)點(diǎn)的確定本文給出了多種方法，本文運(yùn)用了根值 的方法。 基于 人工神經(jīng)網(wǎng)絡(luò) 字母識(shí)別 的特點(diǎn)和優(yōu)越性，主要表現(xiàn)在三個(gè)方面 ： 第一，具有自學(xué)習(xí)功能。 字 母識(shí)別時(shí) ，只在先把許多不同的圖像樣板和對(duì)應(yīng)的應(yīng)識(shí)別的結(jié)果輸入人工神經(jīng)網(wǎng)絡(luò)， 然后在 識(shí)別之前 對(duì)神經(jīng)網(wǎng)絡(luò)進(jìn)行訓(xùn)練形成穩(wěn)定的權(quán)值 這樣 網(wǎng)絡(luò) 通過(guò)自學(xué)習(xí)功能，慢慢學(xué)會(huì)識(shí)別類(lèi)似的圖像。第二，具有聯(lián)想存儲(chǔ)功能 。 用人工神經(jīng)網(wǎng)絡(luò)的反饋網(wǎng)絡(luò) 在字母識(shí)別時(shí) 可以實(shí)現(xiàn)這種聯(lián)想 。 第三，具有高速尋找優(yōu)化解的能力。 字母識(shí)別時(shí) 尋找一個(gè)復(fù)雜問(wèn)題的優(yōu)化解，往往需要很大的計(jì)算量，利用一個(gè)針對(duì)某問(wèn)題而設(shè)計(jì)的反饋型人工神經(jīng)網(wǎng)絡(luò) 的字母識(shí)別系統(tǒng) ，發(fā)揮計(jì)算機(jī)的高速運(yùn)算能力，可能很快找到優(yōu)化解。 本文是在 matlab 環(huán)境下模擬整個(gè)英文字母的識(shí)別過(guò)程，隨著科學(xué)技術(shù)的 發(fā)展識(shí)別技術(shù)更加成熟，各種難 題都將會(huì)得到解決。 關(guān)鍵詞： 字母識(shí)別；圖像處理；特征提取； BP 神經(jīng)網(wǎng)絡(luò)濟(jì)南大學(xué)泉城學(xué)院畢業(yè)論文 II ABSTRACT Today the science and technology develop rapidly. Letter recognition technology based on the feedback neural work is applied in many aspects including publication, finance military, cash register, page views, and any with repeatability,and variability of data files . Letter Identification System include the following processes: preprocessing, feature extraction, BP neural work training,and recognition.. In this paper, we use a threelayer neural work, including input layer, hidden layer and output layer. This paper supply of a variety of methods to determine Hidden layer nodes . The root sign method and other proposed by the Nelson and Illingwnrth are applied . The features and advantages of Artificial neural work is reflected in three aspects : First, a selflearning function. When we recognize letters, only putting many different images and the corresponding results into the artificial neural work and forming a stable weight before the letter recognition,the work will be through selflearning function to slowly identify similar , with the association storage. Artificial neural work feedback work can achieve this association in the letter recognition. Third, finding the optimal solution with high capacity. Finding the optimal solution of a plex often require a large amount of a design that a feedback type artificial neural work for problem and playing the highspeed puting power of puter, you may quickly find the optimal solution. In the matlab environment this article simulate the entire process of letter recognition, with the development of science and technology recognition technology is more mature and have various problems will be solved. Keywords： Letter identification； image processing； feature extraction； the feedback neural work 濟(jì)南大學(xué)泉城學(xué)院畢業(yè)論文 III 目 錄 摘 要 ........................................................................................................... 1 ABSTRACT .......................................................................................................... II 1 前言 .................................................................................................................. 1 研究背景及意義 ..................................................................................... 1 研究現(xiàn)狀 ................................................................................................. 2 手寫(xiě)字母識(shí)別方法 ................................................................................. 3 結(jié)構(gòu)模式識(shí)別方法 .................................................................... 3 統(tǒng)計(jì)模式識(shí)別方法 .................................................................... 3 統(tǒng)計(jì)與結(jié)構(gòu)相結(jié)合的識(shí)別方法 ................................................ 4 人工神經(jīng)網(wǎng)絡(luò)方法 .................................................................... 4 識(shí)別系統(tǒng)性能的評(píng)價(jià) ............................................................................. 5 論文組織結(jié)構(gòu) ......................................................................................... 5 2 預(yù)處理 ................................................................................................................ 6 系統(tǒng)框架 ................................................................................................. 6 預(yù)處理概述 ............................................................................................. 6 本文預(yù)處理設(shè)計(jì) ..................................................................................... 6 去噪 ............................................................................................... 7 二值化 ........................................................................................... 8 歸一化 ...................................................................................... 10 細(xì)化 ............................................................................................. 11 3 字母特征提取 ................................................................................................ 13 特征提取概述 ....................................................................................... 13 本文特征提取設(shè)計(jì) ............................................................................... 13 像素百分比特征 ......................................................................... 14 提取矩陣的粗網(wǎng)格特征 ............................................................. 15 重心特征 .................................................................................... 16 提取圖像的矩陣像素特征 ........................................................ 16 筆劃特征 ..................................................................................... 17 外輪廓特征提取 ........................................................................ 18 4 BP 神經(jīng)網(wǎng)絡(luò) .................................................................................................. 19 人工神經(jīng)網(wǎng)絡(luò) ....................................................................................... 19 神經(jīng)網(wǎng)絡(luò)的模型圖 ..........................