 |
| Image Source: Technology Review |
This article grabbed me with excitement and I'll admit, kind of disturbed me as well. The very busy image above in the paper is Figure 13 for reference. I scanned the article for things like "AI"; "Artificial Intelligence" and found nothing, but 48 and 49 in the paper itself does reference two other papers in IEEE Transactions on Pattern Analysis and Machine Intelligence, for the true believers in Skynet (it's a nerd joke - really!). However, this could be a milestone in image processing, and with the ubiquitous usage of cell phone videos as witness to malfeasance - police or criminal - this could be very important. The technology for facial recognition could be impacted by this advance, then I got concerned again since civil liberties were up for debate with the recent expiration of the Patriot Act and its replacement by the Freedom Act. With technology we walk a tightrope, thinning inexorably to dental floss.
TECHNOLOGY REVIEW: Imagine an oak tree in a field of wheat, silhouetted against a cloudless blue sky on a dreamy sunny afternoon. The chances are that most people reading this sentence can easily picture a bucolic scene in their mind’s eye. This ability to read a description of a scene and then imagine it has always been uniquely human. But this precious skill may no longer be ours alone.
Anyone thinking that these kinds of imaginings are far beyond the ability of today’s computing machines will be surprised by the work of Hiroharu Kato and Tatsuya Harada at the University of Tokyo in Japan.
Today, these guys unveil a machine that can translate a description of an object into an image. In other words, their computer can conjure an image of an external object not otherwise present. That’s a pretty good definition of imagination—in this case of the computational variety.
For sure, these computer imaginings are simple, sometimes confusing and often nonsensical. But the fact they are possible at all represents a significant step forward for computational creativity.
Physics arXiv: Image Reconstruction from Bag-of-Visual-Words
Hiroharu Kato, Tatsuya Harada
No comments:
Post a Comment