Ask Your Question
0

matcher tutorial

asked 2013-10-29 04:04:04 -0500

openedcv gravatar image

updated 2013-10-29 04:11:07 -0500

hi all...

was following the matching tutorial at: http://docs.opencv.org/doc/tutorials/features2d/feature_homography/feature_homography.html#feature-homography

i pretty much used the same code but the results with my own images are not that great. as you can see on the image bellow the mapped key points are not really as densely located as with the example box images. is there a special procedure to follow to prepare the images prior to using this code? i did use grayscale pngs as the example box.png and box_in_scene.png...

here is my result: http://el.net/img/tmp/result.png

thanks...

(also whenever writing a title for a question here an annoying suggest menu is showing up and no matter what or where i am clicking it does not disappear. it just pushes the text of the message to the right)

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted
0

answered 2013-10-29 09:08:51 -0500

ThevenonP gravatar image

I would link to another post with good answer on how to refine matches : http://stackoverflow.com/questions/8118825/how-to-reduce-matches-in-opencv-pattern-recognition

There are several ways to improve the matching performances, basically by making sure that the matches you have found are reliable. I think this is the way to go, rather than trying to improve the preprocessing on your images.

edit flag offensive delete link more

Question Tools

Stats

Asked: 2013-10-29 04:04:04 -0500

Seen: 142 times

Last updated: Oct 29 '13