搜索资源列表
train-images-idx3-ubyte
- 用于手写数字识别的训练数据(图片) 数据格式:前32位为2049,再32位为数据数量,再32位为图片宽度M,再32位为图片高度N,之后每N*M位都是图片的像素值(Training data (pictures) for handwritten digit recognition)
t10k-images-idx3-ubyte
- 用于手写数字识别的预测数据(图片) 数据格式:前32位为2049,再32位为数据数量,再32位为图片宽度M,再32位为图片高度N,之后每N*M位都是图片的像素值(Predictive data (pictures) for handwritten numeral recognition)
Character_Recognition
- 本程序主要参照论文,《基于OpenCV的脱机手写字符识别技术》实现了,对于手写阿拉伯数字的识别工作。识别工作分为三大步骤:预处理,特征提取,分类识别。预处理过程主要找到图像的ROI部分子图像并进行大小的归一化处理,特征提取将图像转化为特征向量,分类识别采用k-近邻分类方法进行分类处理,最后根据分类结果完成识别工作。 程序采用Microsoft Visual Studio 2010与OpenCV2.4.4在Windows 7-64位旗舰版系统下开发完成。并在Windows xp-32位系统下测试
kNN
- KNN算法改进约会网站配对效果;KNN实现手写数字识别(KNN algorithm to improve the matching effect of dating sites; KNN handwritten numeral recognition)
handwrite2
- 采用KNN算法,用PYTHON语言实现的手写数字图像识别(Using KNN algorithm, handwritten digital image recognition with PYTHON language)
深度学习在手写汉字识别中的应用综述_金连文
- 深度学习在手写汉字识别领域中的应用与综述(Application and survey of deep learning in the field of handwritten Chinese character recognition)
MNIST
- 简单的手写数字识别,在深度神经网络中的简单尝试,对于初学者有个很好的理解(Simple handwritten numeral recognition, in the depth of neural network simple attempt, for beginners have a good understanding)
BP神经网络实现手写数字识别matlab实现
- BP神经网络实现手写数字识别matlab实现(Matlab implementation of handwritten digit recognition based on BP neural network)
手写数字识别
- 一个练习机器学习的算法,解决手写数字识别的算法(An algorithm that exercises machine learning to solve the handwritten numeral recognition algorithm)
数字识别
- python的keras调用theano创建cnn识别minist手写数字(use keras of python to create cnn to recognize digit wrote by hand)
Deep-Learning-ToolBox-CNN-master
- 实现CNN的手写字体matlab程序,可调节激活函数,选择loss函数(Realization of handwritten font matlab CNN procedures, can regulate the activation function, loss function)
test1
- 需要tesseract ocr api支持,测试用手写识别(Tesseract OCR API support is required for handwriting recognition test)
mnist1
- 训练手写数字识别算法,正确率达到91.6%(Training handwritten numeral recognition)
14.SVM(代码)
- 用SVM在python平台实现手写数字的识别(using the algorithm of SVM to recognition of handwritten numerals on python)
BP神经网络手写数字识别
- 使用bp神经网络算法识别手写阿拉伯数字图像,三层的误差反馈神经网络,可输出准确率,数据集为60000条数据,每条数据是一张28*28的图片(The BP neural network algorithm is used to recognize handwritten Arabia digital images, and the error feedback neural network of three layers can output the accuracy rate. The data
实验46 手写识别实验
- STM32的手写识别程序。内有详细的注释和文档。很好的学习资料。(STM32 handwriting recognition program. There are detailed notes and documentation. Good study materials.)
MNIST手写数字图片库
- 原图像库,未经过特征提取的手写数字库,可以使用(The original image library, untouched handwritten digital library, can be used)
VC++数字、英文字符、汉字及手写识别实例
- 简单的字符识别程序,能实现手写字符、英文、符号的识别,采用了位图以及预处理(character recognition)
cnn
- 用CNN识别手写数字集,误差率为1.07%(The handwritten numeric set is identified with CNN, the error rate is 1.07%)
Classify handwriten digits
- python下CNN手写数字识别CNN Classify handwriten digits(CNN Classify handwriten digits)