Description: 论文标题:自适应模糊系统在手写体数字识别中的应用研究
作者:张镭
作者专业:计算机软件人工智能
导师姓名:黄战
授予学位:硕士
授予单位:暨南大学
授予学位时间:19990501
论文页数:59页
文摘语种:中文文摘
分类号:TP18 TP391.4
关键词:手写体数字 自适应 模糊逻辑 神经网络 模式识别
摘要:该文针对模式识别的特点,构造了适合于模式识别问题的自适应模糊系统,对三种不同学习算法加以改进,在手写全数字识别上对分类器进行了实现,并与采用BP算法训练的三层前馈神经网络分类器相比较,分析其优劣.仿真实验表明,在该文的样本集条件下,自适应模糊分类吕的识别性能优于神经网络分类器,这充分体现了自适应模糊技术用于数字识别的优越性和潜力.-thesis entitled : adaptive fuzzy system in a handwritten numeral recognition of applied research Author : Zhang Lei professional author : artificial intelligence computer software instructor Name : Huang war conferred degrees : Master award units : Jinan University conferred degrees : 19990501 page thesis : Abstracts 59 languages : Chinese Digest Key words : TP18-image Keywords : handwritten digital adaptive fuzzy logic neural network pattern recognition Abstract : In this paper the characteristics of pattern recognition, suitable for the construction of adaptive pattern recognition fuzzy systems, three different learning algorithm to improve the handwriting recognition on digital classification of the device to achieve, BP and with a three-tiered training algorithm for neural network clas Platform: |
Size: 4194405 |
Author:成东 |
Hits:
Description: 论文标题:自适应模糊系统在手写体数字识别中的应用研究
作者:张镭
作者专业:计算机软件人工智能
导师姓名:黄战
授予学位:硕士
授予单位:暨南大学
授予学位时间:19990501
论文页数:59页
文摘语种:中文文摘
分类号:TP18 TP391.4
关键词:手写体数字 自适应 模糊逻辑 神经网络 模式识别
摘要:该文针对模式识别的特点,构造了适合于模式识别问题的自适应模糊系统,对三种不同学习算法加以改进,在手写全数字识别上对分类器进行了实现,并与采用BP算法训练的三层前馈神经网络分类器相比较,分析其优劣.仿真实验表明,在该文的样本集条件下,自适应模糊分类吕的识别性能优于神经网络分类器,这充分体现了自适应模糊技术用于数字识别的优越性和潜力.-thesis entitled : adaptive fuzzy system in a handwritten numeral recognition of applied research Author : Zhang Lei professional author : artificial intelligence computer software instructor Name : Huang war conferred degrees : Master award units : Jinan University conferred degrees : 19990501 page thesis : Abstracts 59 languages : Chinese Digest Key words : TP18-image Keywords : handwritten digital adaptive fuzzy logic neural network pattern recognition Abstract : In this paper the characteristics of pattern recognition, suitable for the construction of adaptive pattern recognition fuzzy systems, three different learning algorithm to improve the handwriting recognition on digital classification of the device to achieve, BP and with a three-tiered training algorithm for neural network clas Platform: |
Size: 4194304 |
Author:成东 |
Hits:
Description: 手写体识别中，对于阿拉伯数字的识别。常用的模式分类方法都可以应用。这个小程序使用的方法是线性判别分析-Handwriting recognition, for identification of Arabic numerals. Commonly used pattern classification methods can be applied. This small program uses the method is linear discriminant analysis Platform: |
Size: 2048 |
Author:孙家冕 |
Hits:
Description: 手写体识别中，对于阿拉伯数字的识别。常用的模式分类方法都可以应用。这个小程序使用的方法是模板匹配方法-Handwriting recognition, for identification of Arabic numerals. Commonly used pattern classification methods can be applied. This small way is to use a template matching method Platform: |
Size: 1024 |
Author:孙家冕 |
Hits:
Description: 模式识别手写数字分类程序，对0到9十个数字分类。-Handwriting recognition digital classification procedures, 0-9 to 10 the number of categories. Platform: |
Size: 1432576 |
Author:google |
Hits:
Description: 手写分类识别，是个很好的程序，希望大家能用上-Handwriting classification and recognition, is a very good program, hope everyone can be on the Platform: |
Size: 8192 |
Author:王可 |
Hits:
Description: 这是一个能成功运行的非常有用的分类程序,只要用于数字的识别,也就是手写识别,和大家分享-This is a successful run of a very useful classification procedures, as long as for digital identification, that is, handwriting recognition, and to share Platform: |
Size: 5168128 |
Author:zangying |
Hits:
Description: As the years of intensive research and development went by, and with the birth of
several new conferences and workshops such as IWFHR (International Workshop
on Frontiers in Handwriting Recognition),1 ICDAR (International Conference on
Document Analysis and Recognition),2 and others [8], recognition techniques
advanced rapidly. Moreover, computers became much more powerful than before.
People could write theway they normally did, and characters need not have to be written
like specified models, and the subject of unconstrained handwriting recognition
gained considerable momentum and grew quickly. As of now, many new algorithms
and techniques in preprocessing, feature extraction, and powerful classification methods
have been developed [8, 9]. Further details can be found in the following chapters Platform: |
Size: 7475200 |
Author:Kiki |
Hits:
Description: 支持向量机（SVM）是在统计学习理论的基础上发展起来的新一代学习算法，该算法在文本分类、手写识别、图像分类、生物信息学等领域中获得了较好的应用。本书是SVM的权威参考书。-Support Vector Machine (SVM) is a new learning algorithm developed on the basis of statistical learning theory, the algorithm to obtain a better application in the field of text classification, handwriting recognition, image classification, bioinformatics, etc.. This book is the authoritative reference SVM. Platform: |
Size: 4822016 |
Author:wjfwzzc |
Hits:
Description: 堆栈自编码，通过两个稀疏自编码的堆叠和softmax分类模型，实现手写体的分类。-Stack self-encoding, since encoding by two sparse stack and softmax classification model to classify handwriting. Platform: |
Size: 10853376 |
Author:单清序 |
Hits:
Description: 亲自试验出来的对于手写体的LDA分类，最后效果是73.13 ，大家想对LDA了解更深的话可以看看！是matlab版的。
-Personally tested out for LDA classification handwriting, the last effect is 73.13 ,we want a deeper understanding of LDA, then you can see! Is matlab version. Platform: |
Size: 15139840 |
Author:baojunli |
Hits:
Description: VC++ 手写文字识别程序源码。实现手写数字给出不同的分类器识别结果，可心采用模板匹配分类器（最邻近模板匹配法）识别。手写数字或者打开已有的手写数字图像后，在右视图空白处，单击鼠标左键，激活右视图，选择菜单中的各种分类算法，可以对手写数字进行分类。-VC++ handwriting recognition program source code. Handwritten numbers give different classification recognition result satisfying template matching classifier (nearest neighbor template matching) recognition. After the handwritten numbers or open an existing handwritten digital images, view the space on the right and click the left mouse button to activate the right view, the menu of the various classification algorithms can classify handwritten numbers. Platform: |
Size: 620544 |
Author:黄勇 |
Hits:
Description: mnist_dataset,美国中学生手写手写识别数据集，是检验算法分类情况的公共数据集。-Mnist_dataset, American high school students handwritten handwriting recognition data sets, is the public data sets for testing algorithm classification. Platform: |
Size: 22820864 |
Author:陈鑫 |
Hits:
Description: 程序编码：utf8
是否框架：非MVC框架,自己手写普通代码，作为企业用，已经绰绰有余。
程序成熟度：初级
后台界面来源：网络，借鉴yourphp后台，也感谢yourphp.
运行效率：中等，加入数据缓存后性能提高
栏目类别：文章，人员信息，专题项目，招聘，下载，相册，单页【支持无限极分类】
文章：可用作添加新闻，资讯，列表信息类栏目信息
人员信息：可用作企业员工信息栏目内容添加或者维护
专题项目：可用作企业培训项目信息栏目内容添加或者维护
招聘：可用作企业人力资源管理信息栏目内容添加或者维护-Program code: utf8
Whether the framework: non MVC framework, their handwriting common code, as an enterprise, has more than enough.
Program maturity: primary
Background interface source: network, learn the yourphp background, but also thanks to yourphp.
Efficiency: medium, adding data cache performance
Column category: articles, projects, personnel information, recruitment, download, photo album, single page [] support unlimited classification
Article: can be used to add news, information, list information
Personnel information: can be used to increase or maintain the information content of enterprise employees
Special projects: can be used for enterprise training program information column content to add or maintain
Recruitment: can be used for enterprise human resources management information content to add or maintain Platform: |
Size: 11268096 |
Author:wangxinyi |
Hits:
Description: 基于三层神经网络的手写字数据库分类。正确率可达96 ，和适合新手入门-Based on three layers neural network classification of handwriting Accuracy can reach 96 , and is suitable for beginners entry
Platform: |
Size: 2048 |
Author:任强 |
Hits:
Description: 实施KNN算法，并使用KNN改进约会网站，将KNN运用在手写识别系统。(Implement KNN algorithm, and use KNN to improve dating website, use KNN in handwriting recognition system.) Platform: |
Size: 26624 |
Author:青衣可儿
|
Hits:
Search - handwriting classification