在神经网络上应用在线手写 [英] Apply online handwriting on neural network

问题描述

大家好，

我正在从事手写识别android应用程序项目.我应该通过在线识别来识别字符.(我的意思是没有文字或图像).我搜索了很多有关它的网站.我学会了使用神经网络，也学到了如何使用神经网络.但是，我对如何使用用户输入来设置神经网络感到困惑.我应该使用字符点还是将字符转换为图像?然后如何仅使用此输入来创建神经网络?

Hello folks,

I am working on a handwriting recognition android application project. I should recognize characters by online recognition.(I mean there are no words or images). I searched lots of websites about it. I learned that I would use neural network and I also learned how I can use neural network. But, I am confused about how I can set neural network by using inputs from user. Should I use points of characters or turn the characters into image? And then how can I create neural network by just using this inputs?

推荐答案

您在正确的位置上提出您的问题.我在CodeProject文章中发现了有关OCR的大多数信息，特别是使用基于神经网络的方法.请参阅:

神经网络OCR [使用神经网络创建光学字符识别(OCR)应用程序 [神经网络分类器 [使用链码的光学字符识别(OCR)中的AC#项目 [ ^ ]，
Unicode光学字符识别 [ Hebb神经网络 [ C ++中的反向传播人工神经网络 [

You are asking your questions on a right site. Most of the information on OCR, in particular, using the approaches based on neural network, I found in CodeProject articles. Please see:

Neural Network OCR[^],
Creating Optical Character Recognition (OCR) applications using Neural Networks[^],
Neural Network Classifier[^],
A C# Project in Optical Character Recognition (OCR) Using Chain Code[^],
Unicode Optical Character Recognition[^],
Hebb neural network[^],
Backpropagation Artificial Neural Network in C++[^].

Sorry, none of then are in Java, but such tiny a difficulty cannot be a problem for you, can it?

—SA

这篇关于在神经网络上应用在线手写的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！