This is very cool and pretty insightful. The Matrix represents itself perfectly, looking very similar to the code itself. Pan's Labyrinth was also close, and Bambi for that matter. Its interesting to see how closely we associate a movie with the colours in it, even if we dont recognize that association.
Yes, loved the Matrix representation myself too. But then again, look at the Kill Bill one. It's not as "yellow" as I associate with the movie (I think the packaging gives me that "yellow feeling"). But then, there is this one lonesome yellow stripe in the moviebarcode for Kill Bill! I thought that captured the movie well on a higher plane (e.g. main character being quite a lone, too).
That was definitely the one that stood out the most to me. It's always one of the first movies that comes to mind when I'm thinking about color in film.
Agreed, though at times "Hero" is borderline heavy-handed with color. However it manages to remain beautiful. One thing I've learned, though, from a set-designer friend, is that nearly every movie is highly attuned to color and lighting.
If you're looking for other films that use color in interesting ways, check out the "Three Colors Trilogy" by Kieslowski.
Hey, this is really great. I love these apps which turn existing video into new forms of media. If you haven't seen it already, you should check out Cory Arcangel's "Colors PE."
It would be awesome to know the exact details on how these are made. Is it a histogram basis with thresholds to choose which colour is shown, or simply the entire frame compressed to a couple of pixels thick, and then just include some percentage (like 1%) of frames. These are great, you really can tell a lot about a movie, like how long mostly unchanging scenes last, and the overall colour palettes used. Great stuff!
I'm pretty sure it's some straightforward cropping/resizing of some subset of the frames in the movie. The barcode for Slumdog Millionaire[1] presents some pretty compelling evidence that this is the case.
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).
I'd like to know more about the compression technique used as well. It would be nice to know how much "smear" or "lossiness" there is.
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...
I think it is made using a filmstrip of some frames of the movie then streched vertically. I tried to reverse the image to the filmstrip and this is what i've got: the probel is the image is so low res than the frames are recreated with a lot of difficulty. Anyway, i put a actual frame of the movie next to the filmstrip. You can still recognize figures. like body shapes, etc. My try here (Kill Bill vol 1: http://i.imgur.com/ZUUo0.jpg
Given the letter artifacts in "Kill Bill" it looks like they're preserving vertical position. So, possibly making each vertical pixel stripe a horizontal average of several consecutive frames---all pixels at height y in an adjacent batch of a few dozen frames.
If I was to do it I would take every digital frame and then take each pixel from top left to bottom right and make one long chain. Either that or average x neighboring pixels to fit the size vertically. I have no idea how they did this specifically though.
Surprisingly The wizard of Oz was less interesting than I would have thought. Though the scenes in the Emerald city (bookending the assault on the Witch's castle) do jump out.
I'd like to see a movie like Sin City and House of the Flying Daggers :). Really neat idea, but tumblr might not be the best way to display the information.
In some cases, the colors actually do that quite well.
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.
Or for that matter I kind of want to hover over parts of the barcode to see a screenshot from that scene -- I wanna see what that one "red" part is really quickly.
Lots of blues, oranges, and green. I suppose there is either a bias for filmmakers to prefer these colors, or something in the algorithm 'prefers' these colors?
This is why I don't really find the images of much use, but they are still fascinating.
I think the images completely fail to show the spirit of a movie, all they are good for is for _reviving_ the partially lost feeling of a watched movie.
I think they are a great example of computer art.
Interestingly, those shots were filmed using a technique called slit scan photography. Though not quite what you were asking for, someone has reversed that process in order to reveal the original images used to create the effect:
http://seriss.com/people/erco/2001/
This is great! It deserves to be hosted on a dedicated service, though: something with search, at least, and preferably with a link to the software used so that submissions could be crowdsourced.
This could be useful if placed along a timeline in an interface for seeking to a specific scene in a movie or video.
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.
