Ask Your Question

How to do Region Growing Using Average Color as A Seed to Grow Pixels?

asked 2013-07-07 22:05:52 -0500

Shaban gravatar image

Hi all, I'm working on a "killing time" project to detect human using background substraction + classifier, and now the project has been completed. But my application shows some false objects detection are caused by the tree branch shaking, moving bushes, etc.. And now I wanna reduce them using this algorithms:

  1. Utilize the color histogram of object to check whether all the pixels of the object are of one similar color. Because the false object is a part of tree or other background, their pixels have the similar color (Green). If the object is false, the pixel values should be centered by one pixel with maximum probability in color histogram.

  2. Use the technique of the region growing to check whether the object is one part of background. Use the average color as a seed to grow the pixels on vertical direction to form a larger region. If the number of pixels covered by extended region is more than the number of original object, then this object is false.

But I'm still confuse how to convert the algorithms into OpenCV + C++. Are there simple way to do region growing? or any library can help me on region growing?

I'll apreciate any help here. Thanks. :)

edit retag flag offensive close merge delete



This is your killing time project... respect man!

hassan gravatar imagehassan ( 2014-04-04 04:55:32 -0500 )edit

1 answer

Sort by ยป oldest newest most voted

answered 2013-08-08 03:11:18 -0500

theodore gravatar image

i think that you should have a look at the floodfill, watershed and grabcut algorithms. There is also an example in this book.

edit flag offensive delete link more


Are the watershed and region growing algorithms the same ?

BurkDe gravatar imageBurkDe ( 2017-09-19 05:53:50 -0500 )edit

Question Tools


Asked: 2013-07-07 22:05:52 -0500

Seen: 14,163 times

Last updated: Aug 08 '13