Thank you for your fast replies
OpenCV seems the right approach to this problem
I installed the package, and noticed that it's not very Python friendly - no
docstrings, very little documentation on Internet regarding Python and overall
created as abstraction not common for Python
If you don't mind...
I managed to get to list of DMatch objects, from two gray scaled images:
==========
...
feat_det = cv2.FeatureDetector_create('SIFT')
ga_det = cv2.GridAdaptedFeatureDetector(feat_det, 100)
det1 = ga_det.detect(im1g)
det2 = ga_det.detect(im2g)
dsc_ext = cv2.DescriptorExtractor_create('SIFT')
dex1 = dsc_ext.compute(im1g, det1)
dex2 = dsc_ext.compute(im2g, det2)
bf = cv2.DescriptorMatcher_create('BruteForce')
d_matches = bf.match(dex1[1], dex2[1])
==========
Now, I don't see any obvious way to evaluate this list of DMatch objects -
'd_matches'
It seems that drawMatches()
(http://opencv.willowgarage.com/documentation/cpp/features2d_drawing_function_of_keypoints_and_matches.html)
should be called, as in this C++ example:
http://opencv.itseez.com/doc/tutorials/features2d/feature_flann_matcher/feature_flann_matcher.html
but I can't find that function in Python bindings
Do you maybe have experience with OpenCV and further advise?
If not, it's perfectly fine, I wanted to show my appreciation to your
suggestions
Regards,
Matt
------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and
threat landscape has changed and how IT managers can respond. Discussions
will include endpoint security, mobile security and the latest in malware
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
