2015-04-15 08:44:44 -0600 | received badge | ● Favorite Question (source) |
2015-01-19 06:54:33 -0600 | received badge | ● Famous Question (source) |
2014-04-18 13:18:12 -0600 | received badge | ● Notable Question (source) |
2014-02-19 17:32:18 -0600 | received badge | ● Popular Question (source) |
2013-08-08 14:09:01 -0600 | commented answer | FREAK or BRISK neither good nor faster than SIFT/SURF when using BruteForceMatcher Thanks a lot! These really clear up my doubts. |
2013-08-08 13:59:21 -0600 | received badge | ● Scholar (source) |
2013-08-08 03:02:53 -0600 | received badge | ● Student (source) |
2013-08-08 02:14:52 -0600 | asked a question | FREAK or BRISK neither good nor faster than SIFT/SURF when using BruteForceMatcher I try to match images against a database (100 images) to find the best matched image. With OpenCV, I first tried SIFT feature with FlannBasedMatcher and found it worked well. But, because SIFT is patented, I turned to BRISK and FREAK. For both, I used BRISK detector (i.e. AGAST) and BruteForceMachter as they are binary descriptors. As claimed in the original BRISK and FREAK papers, they should have comparable accuracy and be faster than SIFT. But unfortunately the result was really bad. My code of matching part looks like I used a matching Hamming distance threshold of 90 as suggested in the BRISK paper. However, the good_matches contains not so many matches (usually 20 matches or so), out of which only about 25% (or even worse) belong to the correct matched image. This result is much much worse than SIFT where this proportion is commonly over 90%. In addition, they were not faster either. After the train set (100 images) is trained and indexed using FlannBasedMatcher, the matching of SIFT is actually much faster than BRISK/FREAK with BruteForceMatcher. Therefore, I also tried to use FlannBasedMatcher with LshIndexParams for BRISK/FREAK like But the results were still bad and not faster either. So I have two questions here:
Thank you in advance for any hints. |