搜索资源列表
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
BPANN
- 基于BP神经网络的字符识别算法源代码,包括网络仅值训练方法,训练是通 过调用34个字符文件夹,识别率达到99.8 。-BP neural network-based character recognition algorithm source code, including the value of the network only training methods, training is by calling the 34-character file folders, the r
newchar
- 字符识别,MATLAB程序的。可以运行。基于神经网络-Character recognition
huffman
- 车牌识别算法,采用BP神经网络的方法进行车牌字符识别,并能把汉字识别出来。-License plate recognition algorithm, using the BP neural network method for license plate character recognition, and to recognize Chinese characters.
BackPropagation
- 简单的BP神经网络小程序,识别4*4像素大小的A,I,O字符-This is a simple program of backpropagation recognizing the labels of A,I and O.