An international team of research scientists are designing software which will automatically produce aesthetically beautiful images from our snapshots. The team, led by Prof Daniel Cohen-Or at Tel-Aviv University, Israel and Prof Ligang Liu at Zhejiang University, China, have already managed to isolate a number of factors which go towards making an image ‘pleasing’ to the eye, and are now busy incorporating their ideas into their software. These rules are based on traditional composition guidelines, including the famous rule of thirds, diagonal dominance and visual balance. By combining the rules into one program, the researchers have managed to tweak fairly standard snapshots into photos which have that indefinable bit of class.
On the face of it, much of the work seems almost simplistic, a bit of a crop here and there, but the clever bit is the fact that the software not only crops, but also re-positions the important parts of an image into a more pleasing structure – for example moving a tree closer to a second key element to lead the eye properly. Once the re-imaging has been completed, the software then runs through a number of alternative views of the results, and picks the one which it feels is best. All very clever stuff.
It’s not hard to imagine a time in the near future where the fruits of this research will make its way into the chips inside our digital cameras, in the same way that smile and face recognition code already has. In effect we’ll be carrying around a tiny digital David Bailey clone which will create perfection out of our rather average photographic efforts. Is that cheating? What do you think? [Via]
Increasing the aesthetics of a given image is a twofold problem: how to modify the image and how to measure its new aesthetics. The answer to the latter question is the core of our method…Our approach is based on searching, in a low-dimensional parameter space, for the most aesthetic image…Limitations. Professional photographs do not necessarily use the prede?ned aesthetic guidelines, and often chose to disobey them. Our technique follows the guidelines without discretion and does not apply inspiration or creativity. Moreover, our method, similarly to any method that modi?es the relative locations of image parts, may change relative sizes and proportions within the image such that the image semantics are altered.