Object Search Recognition With Mobile Video

Today, I read news about a new technology that researchers at Accenture technology labs have developed. I find it to be amazing. This new technology, called "Pocket Supercomputer," enables phones equipped with video cameras to identify objects in the environment using video search (in reverse so to speak). A demonstration of the "Pocket Supercomputer" can be viewed below. In this demo, the first thing that you will see is, in my opinion, simply amazing when you think about future ramifications. You will see the user take a photo of a book and the phone immediately then reads the title of the book cover back to the user.

Watch what it can do with video as well. Unbelievable technology. Here is an explanation of the technology from the webpage of the project's leader, Fredrik Linaker: Leverages new high-speed low-latency telecommunications and networking infrastructure along with state-of-the art image and sound processing algorithms to create an experience of an always available, immensely powerful and intelligent 'contextually aware' device that fits in the user's palm or pocket. Current working prototype includes full-framerate visual object recognition, audio/video media streaming and recording, motion-controlled camera steering and 3D viewport control, transparent augmented reality overlays, speech generation, and more, all on a standard camera phone or wifi portable device."

There is also an excellent article that I found about this on New Scientist