搜索资源列表
hop
- 霍普菲尔得神经网络字符识别matlab 仿真程序-Hopfield neural network character recognition have matlab simulation program
cnn
- 字符识别 用卷积神经网络识别A-Z26个英文字母-Character recognition using convolution neural network A-Z26 letters
Distortion
- 这是利用神经网络来实现手写字符识别,起准确率已经达到99.26 ,可以继续调整参数达到更深层次的效果。需要自己搭建opencv环境。后期工作可以利用cuda对其更深层次的加速-This is achieved using a neural network handwritten character recognition, since the exact rate has reached 99.26 percent, can continue to adjust the parameters t
newchar
- 字符识别,MATLAB程序的。可以运行。基于神经网络-Character recognition
bp
- c++的bp神经网络字符识别系统可以识别数字字母-c++ bp neural network character recognition system can recognize alphanumeric
神经网络 训练识别
- 1.先打开一幅图片然后按照顺序灰度化、二值化、灰度拉伸、车牌定位、二值化、倾斜校正、字符分割、训练神经网络、识别字符。 2.测试图像存储在当前目录的img下。 3.测试集、训练集、目标向量均存储在img下的文本文件中。(1. First open a picture and then follow the sequence of grayscale, binary, grayscale stretching, license plate positioning, binarization, ti
Lenet
- 卷积神经网络(lenet_5)代码,用于手写字符识别(code of convolutional neural network for handwork characterisic recognation)
dropout_and_minibatch
- 基于两层BP神经网络,加入dropout和softmax,输出层使用softmax,实现对手写字符库MNIST的识别,正确率达90%。(Based on the two level BP neural network, adding dropout and softmax, the output layer uses softmax to realize the recognition of handwritten character library MNIST, the accuracy ra
PR
- 使用qt实现的车牌识别,实现了车牌提取,车牌字符切割以及识别(License plate recognition using QT, license plate extraction, license plate character cutting and identification)