Entries RSS · Intelligent imaging
What does “photo editing” mean? Back in the old days, when coming up with a barely recognizable image was considered a feat, it probably meant nothing. Later on, for professionals and pretty skilled amateurs, it meant playing on successive stages of the chemistry process, using special gases that left particular imprints on the negatives, cutting and adjusting the latter, and so on. And then came the digital era. Nowadays, any mouse-able kid can do practically anything with a photograph: change the lighting, the colors, add a third eye to a friend’s forehead, etc. You get the gist.
But photo editing is changing once again. I came across a couple innovations in photo editing that show that efforts are being channeled towards what can be called “intelligent imaging”. To edit a photo today, you still have to understand the image: you and you alone know what is an object, what is a face, or where this object can (or cannot) realistically be; you and you alone can determine from where the photo should be taken, at what angle, with the focus on which object, etc. “Intelligent imaging” goes beyond that.
Better than a hundred words, two examples should do it:
- The first one is a video of conference by Dave Story, vice president of interactive design at Adobe. The website is in French, but the video at the end (in English) is the interesting part.
- The second one is a technology called “seam carving” (thanks Steve for the pointer), which is being developed in several universities and companies at this moment. The following video explains pretty much most of what there is to know. You can then download an open-source GUI software here if you want to try it out. For other examples and other software (including a Gimp plug-in), you can visit this Flickr group.
[youtube=http://www.youtube.com/watch?v=c-SSu3tJ3ns]
Like
Related posts:
- "Platform as a Service" by SalesForce
- "an iPod, a telephone, an Internet surfing device, an iMicrowave…Are you getting it?" What the iPhone really is
- Software as a Service videos on YouTube
- Open source constraints entrepreneurship
- Bubble or not bubble?
What a great presentation in the video. It shows we’re still at dawn of intelligent digital signal processing for images despite the fact that we’ve been talking about photo editing for ages.
If one ‘fixed’ image can be turned upside down, and customized and improved in such a way, then can you imagine what can be done with videos?? Emmanuel, what’s your opinion on this matter?
I’m really not an expert on video, but surely it will come to that, the additional problem being the recognition of objects between frames (telling that this crouching man it the bottom of the image is the same one as the jumping one two frames later). It is possible (today, in photoshop, gimp or equivalent) to draw very roughly on a shape, and the editing software will then adjust the rough outlining to match the exact shape: I imagine it would be possible (maybe even easy) to do the same to ‘guide’ the recognition software between frames to tell it “this is the same object” – and then some kind of interpolation would allow to link all frames together.
Nice links, I didn’t know about the first one. You could also have mentioned this incredible video demonstration http://labs.live.com/photosynth/blogs/Photosynth+At+TED+Conference.aspx which seems to be closer to existence than the Adobe product.
The technology has been bought by a company: http://www.dpreview.com/news/0801/08011801onone.asp