Ask Your Question
0

Open CV & C++

asked 2013-03-27 18:05:25 -0600

MM gravatar image

my program depend on matching between input image and my database images

then it have for each image (input , database images) locs and descriptors

then i want to save locs and descriptors of database images in to skip list data structure

then what i want is how to sort those locs and descriptors which found in to skip list ?? and how to make the search easily between input and what similar to image in DB to match between them ?? and how able them not to spend more time ??

edit retag flag offensive close merge delete

Comments

No idea why you changed your subject, probably to boost this question, but please adjust it to a correct discription. it is making no sense now :)

StevenPuttemans gravatar imageStevenPuttemans ( 2013-03-28 05:12:45 -0600 )edit

@steven this is another account and the first account is made by my friend who with me in GP and i changed it to be another question to descrip what i want :)

and please if you have a replay to this questions write it ,, and thanks to your notice about the subject of my question :)

MM gravatar imageMM ( 2013-03-28 12:20:26 -0600 )edit

1 answer

Sort by ยป oldest newest most voted
1

answered 2013-03-28 03:02:18 -0600

Here, I assume you are using a bag-of-words like approach. Therefore, you have histograms of your descriptors, which seems more efficient in your case. The idea is to build a tree of histograms. You can use different solutions:

  • a binary tree on each bin: if the bins is greater than the mean, go left, otherwise go right, and so one
  • a binary tree on half(third/...) of histogram's bins
  • cluster your histograms with a metric (intersection, chi-square, Bhattacharyya,...) and build a spatial grid according to the neigborhood (KNN).

I think there is many others solutions, but I'm not familiar with image retrieving optimization, try Google it and read some papers... This is only the "first" solutions I will use if I have to do something similar. Let us know the methods you've try!

Enjoy.

edit flag offensive delete link more

Comments

@ Mathieu Barnachon Thanks alot for your replay :) :) and i will try this Inshaa'ALLAH :)

MM gravatar imageMM ( 2013-03-28 12:23:39 -0600 )edit

Question Tools

Stats

Asked: 2013-03-27 18:05:25 -0600

Seen: 372 times

Last updated: Mar 28 '13