2019-06-10 02:16:29 -0600 | received badge | ● Notable Question (source) |
2017-05-08 15:06:39 -0600 | received badge | ● Popular Question (source) |
2016-01-16 06:47:07 -0600 | received badge | ● Student (source) |
2013-02-14 08:00:52 -0600 | commented answer | What is the best solution for rotation invariant detector? Could you provide some more information about how to achieve this in OpenCV? |
2013-02-14 08:00:01 -0600 | commented answer | What is the best solution for rotation invariant detector? I need to detect logos, not faces, moreover, input images could be in grayscale. |
2013-02-14 01:22:15 -0600 | asked a question | What is the best solution for rotation invariant detector? I'd like to create an object detector based on cascade classifier, the only problem is that LBP and Haar features are not rotation invariant. There are many rotation invariant detectors, for example, iPhone recognizes faces in real time in any orientation, so I wonder how do they achieve this? The first thing that comes to my mind is to rotate the training sample at different angles, but I doubt that the resulting classifier would have good quality, moreover, the object could have stretched proportions. |
2012-12-10 04:46:25 -0600 | asked a question | Measure of difference in Fourier space I'm using FFT to compare two images, but I don't realize what measure should I use to compute similarity between images in Fourier space. Cross-correlation doesn't seem a good choice. |
2012-12-05 02:54:00 -0600 | asked a question | Rotation invariant object detection I'm trying to find an approach to detect stamps on scanned documents. Now I'm considering Haar or HOG features with cascade classifier, but as I know they are not rotation invariant, which makes them not suitable. What alternative can be used is this case? |