搜索资源列表
Handwritten_recognition_system
- Visual C++数字图像模式识别典型案例:手写体数字识别系统-Visual C++ digital image pattern recognition typical case: handwritten digital recognition system
bijishibie
- 基于纹理分析笔迹鉴别系统的设计与实现,文中从笔迹图像预处理、特征提取、分类器以及分类器组合等方而展开研究,设计和实现了一个基于文本独立的离线手写体笔迹鉴别系统软件.-Design and Implementation of the writer identification system based on texture analysis, the paper from the handwriting image preprocessing, feature extraction, classi
20130413
- 基于神经网络的脱机手写体数字识别的代码,能运行-Based on the offline handwritten digital identification code of the neural network, able to run
my_bwmorph
- 该方法主要是用于对手写体汉字的识别处理,处理的比分为汉字的骨架-The method for handwritten Chinese character recognition processing, handling score for the skeleton of the Chinese characters
NumberHandwritting
- 基于神经网络的手写体数字识别,它是用matlab实现的,其中用3种不同的神经的网络方法实现了手写体数字的识别,非常利于初学者的学习和交流。-Handwritten digit recognition based on neural networks, which is achieved using matlab, in which three different neural network to achieve the recognition of handwritten digits, is
CNNhandwrittencharreccssource
- CNN卷积神经网络 手写体识别 c#实现源代码。很好很经典。-Csharp version convolutional neural network . according to the source code adapted from Mike. CNN convolutional neural networks for research of the people.
Handwritten-recognition
- 用BP算法设计分类器,实现对UCI 机器学习数据库中0-9 这10 个手写体数字的训 练和测试。-BP algorithm designed classifier, to achieve the UCI machine learning database 0-9 10 handwritten digits training and testing.
gailvwangluoduishouxietideshibie
- 基于概率神经网络的手写体数字识别,可以尝试作文字图像的辨识- the programm of neural network
Exercise5-Softmax-Regression
- 斯坦福深度学习教程中关于softmax regression的练习代码,源代码中需要补全的地方,全部把代码补完整,把手写体识别的数据库放到路径下,可以直接运行-Stanford deep learning tutorial exercises on softmax regression code, source code need to fill all places, all the full complement of the code, the handwriting recognitio
Exercise6-Self-Taught-Learning
- 斯坦福深度学习教程中关于Self-Taught的练习代码,源代码中需要补全的地方,全部把代码补完整,把手写体识别的数据库放到路径下,可以直接运行-Stanford deep learning tutorial exercises on Self-Taught code, source code need to fill all places, all the full complement of the code, the handwriting recognition into the pat
Exercise7-stacked-autoencoder
- 斯坦福深度学习教程中关于stacked autoencoder的练习代码,源代码中需要补全的地方,全部把代码补完整,把手写体识别的数据库放到路径下,可以直接运行-Stanford deep learning tutorial exercises on stacked autoencoder code, source code need to fill all places, all the full complement of the code, the handwriting recognit
Exercise8-linear-decoder
- 斯坦福深度学习教程中关于linear decoder 的练习代码,源代码中需要补全的地方,全部把代码补完整,把手写体识别的数据库放到路径下,可以直接运行-Stanford deep learning tutorial exercises on linear decoder code, source code need to fill all places, all the full complement of the code, the handwriting recognition into
Handwriting
- 手写识别(HandWriting Recognition)是指将在手写设备上书写时产生的有序轨迹信息化转化为汉字内码的过程,实际上是手写轨迹的坐标序列到汉字的内码的一个映射过程,是人机交互最自然、最方便的手段之一。 随着智能手机、掌上电脑等移动信息工具的普及,手写识别技术也进入了规模应用时代。 手写识别能够使用户按照最自然、最方便的输入方式进行文字输入,易学易用,可取代键盘或者鼠标。用于手写输入的设备有许多种,比如电磁感应手写板、压感式手写板、触摸屏、触控板、超声波笔等。 手写识别属
Handwritten-character-recognition
- 基于字符识别的手写体生成程序,用于图像图形处理,可供参考-Handwritten character recognition based generation program
Hand-writes-number-recognition
- 用C++写的手写数字识别程序,能够比较准确的识别大部分手写体数字。-Written by C++ handwritten numeral recognition program that can more accurately identify most of the handwritten numerals.
mnistAll
- mnistAll数据库,手写体数字识别数据库。里面有分好的训练与测试样本集及对应标签-mnistAll databases, handwritten digit recognition database. There are good training and testing sample sets and the corresponding label
dataset_618531
- 包含1593手写体数字0 ~ 9。从semeion.data通过MATLAB semeion.mat,可以直接使用。原semeion.names为自述。M。 Mat:1593×266 每一个行为样本,其中256是手写数字的16×16,在10栏的数字识别标签,例如:如果第一行是1,然后是0号,其次是1,1。等等。 在Matlab的小例子,可以得出每一个数字,一个更好的理解。你想翻转和旋转的是写作的习惯相一致的图像。-Contains 1593 handwritten digit 0~9
recognize-letters
- 这是一个VC++程序,能识别手写体字母和打印体字母,识别率90 -To recognize the handwritten and printed letters
handwritten-digits_recognition-
- 一个基于神经网络的手写体数字识别的matlab程序,可以自行进行神经网络训练并识别给出相应的结果-A neural network-based handwritten numeral recognition matlab program, the neural network can be trained to identify themselves and give the corresponding results
mnist
- mnist手写体数据库,适合用于做手写数字方面的实验-mnist handwritten database suitable for doing experimental aspects of handwritten digits