从哪里开始使用神经网络进行手写识别? [英] Where to start Handwritten Recognition using Neural Network?
问题描述
我一直在尝试学习神经网络一段时间,我可以在线了解一些基础教程。现在我想用神经网络开发在线手写识别。所以我不知道从哪里开始?我需要一个非常好的指导。最后,我是java程序员。
I've been trying to learn about Neural Networks for a while now, and I can understand some basic tutorials online. Now i want to develop online handwritten recognition using Neural Network. So i haven't any idea where to start? And i need a very good instruction. In finally i'm java programmer.
你建议我做什么?
推荐答案
在 Unipen 数据库中通过字符识别开始简单。
Start simple with character recognition on the Unipen database.
您需要从原始轨迹数据中提取相关要素,以形成通常所说的特征向量。例如,您可以使用插值方案重新采样数据,最终得到n个元组,每个元组包含以下信息:
You will need to extract pertinent features out of raw trajectory data in order to form what's commonly called a "feature vector". For instance you could resample the data using an interpolation scheme to end up with n tuples, each tuple containing information such as:
- position
- 方向
- 速度
- 加速
- 曲率
- etc
- position
- orientation
- velocity
- acceleration
- curvature
- etc
一旦你有一个固定大小的特征向量,你就可以用它作为神经网络的输入。尝试使用MLP网络。
Once you have a fixed size feature vector, you use it as the input to your neural network. Try MLP networks for a start.
您必须进行试验才能确定最佳功能。
You will have to experiment in order to decide which features are best.
如果您需要开始从Ink数据中提取功能,请查看 HP的Lipi工具包(请注意他们的识别器不使用神经网络。)
If you need to get started on extracting features from Ink data, have a look at HP's Lipi Toolkit (note that their recognizers don't use neural networks though).
你也可以看看这个实施神经网络教程的15个步骤。
这篇关于从哪里开始使用神经网络进行手写识别?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!