基于反向传播神经网络的光学字符识别

Shyla Afroge, Boshir Ahmed, F. Mahmud
{"title":"基于反向传播神经网络的光学字符识别","authors":"Shyla Afroge, Boshir Ahmed, F. Mahmud","doi":"10.1109/ICECTE.2016.7879615","DOIUrl":null,"url":null,"abstract":"This paper represents an Artificial Neural Network based approach for the recognition of English characters using feed forward neural network. Noise has been considered as one of the major issue that degrades the performance of character recognition system. Our feed forward network has one input, one hidden and one output layer. The entire recognition system is divided into two sections such as training and recognition section. Both sections include image acquisition, preprocessing and feature extraction. Training and recognition section also include training of the classifier and simulation of the classifier respectively. Preprocessing involves digitization, noise removal, binarization, line segmentation and character extraction. After character extraction, the extracted character matrix is normalized into 12×8 matrix. Then features are extracted from the normalized image matrix which is fed to the network. The network consists of 96 input neurons and 62 output neurons. We train our network by proposed training algorithm in a supervised manner and establish the network. Eventually, we have tested our trained network with more than 10 samples per character and gives 99% accuracy for numeric digits (0∼9), 97% accuracy for capital letters (A∼Z), 96% accuracy for small letters (a∼z) and 93% accuracy for alphanumeric characters by considering inter-class similarity measurement.","PeriodicalId":6578,"journal":{"name":"2016 2nd International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE)","volume":"18 1","pages":"1-4"},"PeriodicalIF":0.0000,"publicationDate":"2016-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"35","resultStr":"{\"title\":\"Optical character recognition using back propagation neural network\",\"authors\":\"Shyla Afroge, Boshir Ahmed, F. Mahmud\",\"doi\":\"10.1109/ICECTE.2016.7879615\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper represents an Artificial Neural Network based approach for the recognition of English characters using feed forward neural network. Noise has been considered as one of the major issue that degrades the performance of character recognition system. Our feed forward network has one input, one hidden and one output layer. The entire recognition system is divided into two sections such as training and recognition section. Both sections include image acquisition, preprocessing and feature extraction. Training and recognition section also include training of the classifier and simulation of the classifier respectively. Preprocessing involves digitization, noise removal, binarization, line segmentation and character extraction. After character extraction, the extracted character matrix is normalized into 12×8 matrix. Then features are extracted from the normalized image matrix which is fed to the network. The network consists of 96 input neurons and 62 output neurons. We train our network by proposed training algorithm in a supervised manner and establish the network. Eventually, we have tested our trained network with more than 10 samples per character and gives 99% accuracy for numeric digits (0∼9), 97% accuracy for capital letters (A∼Z), 96% accuracy for small letters (a∼z) and 93% accuracy for alphanumeric characters by considering inter-class similarity measurement.\",\"PeriodicalId\":6578,\"journal\":{\"name\":\"2016 2nd International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE)\",\"volume\":\"18 1\",\"pages\":\"1-4\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-07-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"35\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 2nd International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICECTE.2016.7879615\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 2nd International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICECTE.2016.7879615","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 35

摘要

本文提出了一种基于人工神经网络的前馈神经网络英语字符识别方法。噪声被认为是影响字符识别系统性能的主要因素之一。我们的前馈网络有一个输入层,一个隐藏层和一个输出层。整个识别系统分为训练和识别两个部分。这两个部分都包括图像采集、预处理和特征提取。训练和识别部分还包括分类器的训练和分类器的仿真。预处理包括数字化、去噪、二值化、线分割和特征提取。字符提取后,将提取的字符矩阵归一化为12×8矩阵。然后从归一化后的图像矩阵中提取特征,并将其送入网络。该网络由96个输入神经元和62个输出神经元组成。我们用提出的训练算法以监督的方式训练网络,并建立网络。最终,我们用每个字符超过10个样本测试了我们的训练网络,通过考虑类间相似性测量,数字数字(0 ~ 9)的准确率为99%,大写字母(A ~ Z)的准确率为97%,小写字母(A ~ Z)的准确率为96%,字母数字字符的准确率为93%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Optical character recognition using back propagation neural network
This paper represents an Artificial Neural Network based approach for the recognition of English characters using feed forward neural network. Noise has been considered as one of the major issue that degrades the performance of character recognition system. Our feed forward network has one input, one hidden and one output layer. The entire recognition system is divided into two sections such as training and recognition section. Both sections include image acquisition, preprocessing and feature extraction. Training and recognition section also include training of the classifier and simulation of the classifier respectively. Preprocessing involves digitization, noise removal, binarization, line segmentation and character extraction. After character extraction, the extracted character matrix is normalized into 12×8 matrix. Then features are extracted from the normalized image matrix which is fed to the network. The network consists of 96 input neurons and 62 output neurons. We train our network by proposed training algorithm in a supervised manner and establish the network. Eventually, we have tested our trained network with more than 10 samples per character and gives 99% accuracy for numeric digits (0∼9), 97% accuracy for capital letters (A∼Z), 96% accuracy for small letters (a∼z) and 93% accuracy for alphanumeric characters by considering inter-class similarity measurement.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信