lukassz's profile - activity

I use the background substraction to detect hand. http://docs.opencv.org/trunk/doc/tuto... Then I would like to outline just a hand. To get rid of imperfections from the background. http://docs.opencv.org/doc/tutorials/... But the method is all the contours. I would like to alb contoured those elements which have larger area than, for example. 200px. How to do it? There is a better method to obtain the same hand in the picture?

@break I'm sorry, I corrected.

It uses background subtraction to detect the same hand in the picture. I used are: http://docs.opencv.org/trunk/doc/tuto...

However, this does not always check the background is sometimes distorted. I will now outline the rest and paste these on a clean background. I have read the function to the stroke, but she contour everything. I would like to outline the area arose then when the area will have more than, for example. 200px http://docs.opencv.org/doc/tutorials/...

I would like to outline appeared on the objects that are larger than 200px area.

Thank for comment. Skin color detection does not always work. better to cut out the background so I think.

Purpose of my application is to take a photo hand (gesture) and comparing it with a picture that is in the database. The first option I was use is background subtraction on images:

http://docs.opencv.org/trunk/doc/tuto....

The solution works, but sometimes, depending on the first picture is not properly cut hand.

The second option is to detect skin color: http://bytefish.de/blog/opencv/skin_c...

Or is it better to use a hand detection based on xml files? To compare the images I wanted to use this method:http://docs.opencv.org/doc/tutorials/imgproc/histograms/histogram_comparison/histogram_comparison.html

Let me remind you that I'm talking about comparing the images to which they are gestures. I also read about the possibility of making the histogram is not the entire image only on the subject of the photo and then the data is more reliable, but do not know how to do it.