Skip to content

Instantly share code, notes, and snippets.

@holys

holys/gist:4547375

Last active December 11, 2015 04:48
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save holys/4547375 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save holys/4547375 to your computer and use it in GitHub Desktop.
Download ZIP
practice *nix command line
@holys
Copy link
Copy Markdown
Author

holys commented Apr 3, 2013

库python的没用过,说说图像处理的思路吧

1,拿图(废话)
2.图拿到后,直接灰度化+二值化一次
3.由于基本无噪声且无粘连现象,对于二值图垂直投影一次,得到投影曲线
4.投影曲线找凹点,切为4个区域,
5.每个区域找上下左右边界,切割
6.尺寸归一化
7.识别--办法很多,我刷了几次,只有数字字母,做个模板库,比对吧;复杂的就要分类了,分类就有很多高深方法了,svm,神经网络,特征统计...具体实现跟方法就有关系了

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment