Moviebarcode - Movies compressed to a single frame

http://iwdrm.tumblr.com/post/2927811283

I've been staring at it for minutes.

http://colors-personal-edition.coryarcangel.com/

Now just free-wheel brainstorming here... but it seems to me that given an acceptably "clean" compression of the video, one could generate a good fingerprint from the hashes of the histograms of each frame.

Then a client-side app could sample a reasonable number of frames and given an algorithm for finding invariant histograms (given changes in lighting, capture quality, etc the algorithm would output a deterministic histogram within some acceptable but narrow tolerance) it could generate a fingerprint that is good enough for a heuristic algorithm to search a database of movie fingerprints...

essentially, shazam for video.

That barcode has a persistent pattern in its lower part: every once and a while, there's the same four light blue lines straddling three sets of light grey lines. That movie is about a contestant on the Indian version of "Who Wants to Be a Millionaire". For reference, I found a screencap of the show on Wikimedia[2]. You'll notice that the location and pattern of the lines in the barcode correspond with the location and form of the question boxes in the show. The light blue lines are the outlines of the boxes, and the light grey ones are the text. I don't have a copy of the movie with me, but I suspect that if you linearly interpolate between horizontal position in the barcode and temporal position in the movie, then the scenes where the question boxes are on the screen will correspond with the locations in the barcode where the pattern appears.

As to whether the frame is cropped or resized to be 1-pixel wide, my guess is that they are resized. My reasoning is that if the frame were cropped, then you might not always see the light grey lines along with the light blue lines in the barcode, since you might take a slice of the frame that falls along spaces between words in the questions and answers. Since the appearance of the question box pattern is pretty much uniform, it's probable that the entire frame is resized, so each pixel in each slice corresponds to the "average" color value of pixels at that height in the sampled frame (I say "average" because I don't really know how downscaling algorithms work).

[1]: http://s3.amazonaws.com/data.tumblr.com/tumblr_lh9wkoPf5s1qh... [2]: http://upload.wikimedia.org/wikipedia/en/thumb/a/a4/Ken_Basi...

A discussion using mplayer for faster output is also attached at http://projects.metafilter.com/2996/Make-your-own-Movie-Barc...

I'd love a script that takes a batch of movies, feeds them to ffmpeg or something and slowly makes barcodes for my movie collection.

For example, look at The Fifth Element. You see that patch of white between the beginning and the middle? That's the scene where Leelo is brought back, I believe. It's the only scene in the movie that I can think of where there's a significant amount of white (although it's possibly Corbin's apartment...). It struck me how recognizable it was before I saw your post, actually.

http://moviebarcode.tumblr.com/post/3432026155/2001-a-space-...

Representations like this are also sometimes used for automatic shot boundary detection (vertical edges in this type of image = an edit to a different camera shot) in video content retrieval systems.