搜索资源列表
dnn
- 用TensorFlow搭建神经网络，识别手写数字(building the neural network by using TensorFlow to identify mnist dataset)
Handwritten_numeric_recognition
- 基于keras深度学习框架的手写数字字符识别(Handwritten numeric character recognition based on keras depth learning framework)
neural_network.tar
- 用于识别手写的0~9，10个数字,使用的工具是matlab(used to identify handwritten number 0~9 ,ten digits)
meehod-datagram-exception
- 联机数字手写识别,模式识别中很基础的程序,也是基于点轨迹的识别()
Run_MNIST
- 下载MNIST数据集(手写体数字0-9)后，搭建卷积神经网络，将输入的数据集经过一层一层的卷积，到最后计算交叉熵，用梯度下降算法去优化它，使它变得最小，这就训练出了权重和偏置量，识别的准确率为91%(Download the MNIST data set (handwritten number 0-9), build a convolutional neural network, the input data set by convolutional layers, finally calcul
KNN python
- 关于K近邻算法的简单实现和一些例子，其中包括手写数字的识别(Simple implementation of K nearest neighbor algorithm and some examples)
标准库
- 用于车牌字符识别系统中的模板匹配识别法，模板库的简历，含数字字母和汉字(Template matching recognition method for license plate character recognition)
Tensorflow CNN
- 卷积神经网络识别手写数字，放在jupyter直接跑，99%识别率，已经和Tensorboard联通好了(Convolutional neural network recognizes handwritten numerals and runs directly on jupyter. The recognition rate is 99%. It has been connected with Tensorboard.)
DeepLearnToolbox-master
- CNN,DBN算法可以对手写体数字进行识别，准确率高(CNN and DBN algorithm can recognize handwritten numerals with high accuracy)
MATLAB-LeNet5-master
- 手写体识别 lenet5 LeNet5由7层CNN（不包含输入层）组成，上图中输入的原始图像大小是32×32像素，卷积层用Ci表示，子采样层（pooling，池化）用Si表示，全连接层用Fi表示。下面逐层介绍其作用和示意图上方的数字含义。(Lenet5 is composed of seven layers of CNN)
RBF
- 基于RBF的手写数字图像识别，matlab程序，欢迎下载交流(Based on RBF handwritten digital image recognition, matlab program, welcome to download and exchange)