News for hackers. Stuff that matters.
Re:Audio Fingerprinting with Python and Numpy (2013) by dylan604 on Saturday October 01, 2016 @12:09AM (#12616474)
In the past, I've been in discussions on using a fingerprinting technique for videos. Provide a small clip of a movie, and out pops the title of the movie. This was always intended to be used on a small and well defined library, and never intended to be used on something like youtube.

One major problem with video is that you could have SD/HD versions and/or full frame/original aspect ratio types of differences of the same movie. One idea I wanted to play with was to detect edit points. The number of frames between edits could be used as the fingerprints. The entire concept was never anything more than a thought exercise. For the purpose of the exercise, we had to assume that there is no audio with the picture.

There are a lot of FFT libraries to process image data since most image compression techniques use some sort of FFT. Would this same type of fingerprinting be able to be used for a visual image. Could the amplitude of the RGB frequencies be used over time? The data set would increase with 3 channels of color, but would it also not help decrease false positives by making the combinations more unique?

Re:Audio Fingerprinting with Python and Numpy (2013) by jwatte on Saturday October 01, 2016 @12:23AM (#12616506)
SD vs HD is largely a solved problem in academia -- the key phrase is "resolution independence." Also, some robustness to cropping, scaling, and flipping is desired in robust fingerprinting systems.
Re:Audio Fingerprinting with Python and Numpy (2013) by lovelearning on Saturday October 01, 2016 @01:42AM (#12616648)
Just thinking out loud, perhaps start with calculating perceptual hashes [1] of frames in both videos and use the inter frame hash distances of videos as fingerprints. As I understand it, perceptual hashing is robust against both resolution and color variations.

[1]: http://www.hackerfactor.com/blog/?/archives/432-Looks-Like-I...

Re:Audio Fingerprinting with Python and Numpy (2013) by soruly on Saturday October 01, 2016 @05:06PM (#12619873)
I suggest using LIRE. You may study my use case here. http://www.semanticmetadata.net/2016/03/04/lire-use-case-wha...
Re:Audio Fingerprinting with Python and Numpy (2013) by regularfry on Saturday October 01, 2016 @03:07AM (#12616842)
If you want to detect edits, you don't need an FFT. At an edit point, the whole image changes almost instantly (ignoring swipes). That means you just need the sum of per-pixel diffs from one frame to the next to be above some threshold.