With photos, out-of-focus used to be a permanent condition. Not any more. De-blurring algorithms, written by people who paid lots of attention in math class, reduce and sometimes almost eliminate several kinds of blurring: incorrect focus, motion blur, and Gaussian blur.
Moscow-based image processing guru Vladimir Yuzhikov has created SmartDeblur, a Windows application that does a remarkable job of making blurry images less blurry. Basically, the blurred bits in an image follow patterns that can be traced backwards mathematically. Deliberately blurred signs, serial numbers, and licenses can be adjusted enough to make them legible again. If you thought you used enough Photoshop Gaussian blur to mask your car’s front plate before Facebook-posting “Me driving at speed on Cannonball Run,” think again. It also has the potential to make smartphone cameras perform better.
“Many people think that blurring is an irreversible operation and the information in this case is lost for good, because each pixel turns into a spot, everything mixes up, and in case of a big blur radius we will get a flat color all over the image,” Yuzhikov says. “But it is not quite true — all the information just becomes redistributed in accordance with some rules and can be definitely restored with certain assumptions.” In other words, the sharp image isn’t dead, only sleeping.
The before/after samples here look pretty good considering how out-of-focus the before originals were. These are Yuzhikof’s samples. “The result is impressive… but in practice not everything is so good,” Yuzhikov writes on his site. Try it yourself and you’ll see improvement but not necessarily as much as the man who wrote the (code) book got. You may find out of focus images work better than images blurred by camera shake (low exposure speeds, shooting from a moving vehicle).