简体   繁体   中英

What would be the best way to isolate these squares?

I've been following this tutorial , but the problem is, my squares have illustrations on it, which causes opencv to pick up on those as well. At least, I think that's what the problem is.

Original image:

在此处输入图片说明

I am aware this might work better with a black background but this is all I have to work with for now.

This is the result of my attempt:

在此处输入图片说明

windows, python2, opencv3.3-dev

Try to process the S channel in HSV space like this.

  1. convert to hsv
  2. seperate the s-channel
  3. threshold the s-channel
  4. some other post-process(such as morph-op)

在此处输入图片说明

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM