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: 基于神经网络的手写体识别程序，可能对感兴趣的朋友有所帮助-Based on neural network handwriting recognition program may be helpful to interested friends Platform: |
Size: 207872 |
Author:zhu |
Hits:
Description: 本程序基于 BP 神经网络完成了对用户使用鼠标输入的特定手势的识别，并且可以学习
用户创建的新手势。程序中已经存储的手势是 Palm 系列掌上电脑中手写识别专用的
Graffiti 字体的数字 0～9，这种字体的特点是每个字由一个连续笔划构成，适合用一个连贯的鼠标手势表示： -This procedure based on BP neural network was completed using the mouse to the user input of a specific gesture recognition, and users can learn to create new gestures. Procedures have been stored in the Palm series of hand gestures is a computer dedicated Graffiti handwriting recognition digital fonts 0 to 9, the font of each word is characterized by a continuous strokes by the composition, for consistency with a mouse gesture, said: Platform: |
Size: 296960 |
Author:郑强 |
Hits:
Description: 数字识别，识别手写体。 使用神经网络算法编写。 识别率一般，带训练功能
-Numeral recognition, handwriting recognition. The preparation of the use of neural network algorithm. Recognition rate of the general, with the training function Platform: |
Size: 83968 |
Author:hbei |
Hits:
Description: 采用神经网络实现手写识别的一种方法，建立Bp神经网络，采用快速训练方法，可快速完成一类相关手写字体的模式识别，识别率较高，当字体变化较大识别率降低时，可重新训练具有较强的适应性。实验证实本方法较好实现了手写字符识别，但也存在识别速度较慢，有时训练不收敛等缺点-Handwriting recognition using neural network is a way to establish Bp neural network, using fast training methods, and can be related to the completion of a class of handwriting pattern recognition, recognition rate higher recognition rate when the font changed greatly reduced, they can re- Training has strong adaptability. Experiments confirmed that this method achieved a better handwritten character recognition, but there are also identified slow, and sometimes non-convergence of the training deficiencies Platform: |
Size: 105472 |
Author:caoliang |
Hits:
Description: 《精通VisualC++数字图像处理模式识别技术及工程实践》介绍了模式识别和人工智能中的一些基本理论，以及一些相关的模型，包括贝叶斯决策、线性判别函数、神经网络理论、隐马尔可夫模型、聚类技术等，同时结合模式识别中的一些问题，比如字符识别、笔迹鉴定、人脸检测、车牌识别、印章识别以及遥感图片、医学图片处理等内容，从多种角度，介绍了解决这些问题的思路-" Proficient in VisualC++ digital image processing, pattern recognition technology and engineering practice," describes the pattern recognition and artificial intelligence in some of the basic theory, and a number of related models, including Bayesian decision-making, linear discriminant function, neural network theory, hidden Markov Cardiff model, clustering technologies, combined with pattern recognition in a number of issues, such as character recognition, handwriting identification, face detection, license plate recognition, seals, and remote-sensing image recognition, medical image processing and other content, from several angles, introduced ideas to solve these problems Platform: |
Size: 11152384 |
Author:吴晶 |
Hits:
Description: 用C#实现的基于神经网络的手写识别程序，还是很不错-Using C# implementation of handwriting recognition based on neural network program Platform: |
Size: 40960 |
Author:赵华 |
Hits:
Description: 可以进行包括bp神经网络以及svm支撑向量机和其他多种方式的模式识别进行数字识别，可以导入白底黑字的图片，也可进行手写识别。-Bp neural network can be included, and svm support vector machines and other pattern recognition in many ways digital identification, black and white images can be imported, but also the handwriting recognition. Platform: |
Size: 5950464 |
Author:daviddy |
Hits:
Description: 基于神经网络的手势识别程序 手写输入原理的演示-Gesture Recognition Based on Neural Network program demonstrates the principle of handwriting input Platform: |
Size: 48128 |
Author:Big Boss |
Hits:
Description: 为了实现对手写字体的识别，运用了人工智能的分层神经网络思想，对识别的字体通过训练学习，达到识别手写字体的功能。-to realize the recognition of handwritten font, using hierarchical neural network artificial intelligence, to identify fonts through training and learning, to identify the handwriting function.
Platform: |
Size: 84992 |
Author:bbb |
Hits:
Description: 本文主要实现手写数字识别，利用多类逻辑回归与神经网络两种方法实现,并编写有GUI界面。(This paper mainly implements handwritten numeral recognition, using multiple logic regression and neural network to achieve two methods, and the preparation of a GUI interface.) Platform: |
Size: 197632 |
Author:洛克刘
|
Hits:
Search - handwriting recognition neural network