One of the biggest problems teachers face is how to find content to use with their students. Youtube has centuries of videos you can watch for free and yet it’s very hard to find what you are looking for. It’s easy to find a video with cats, but it’s much harder to find one with a cat sitting on a brown couch playing with a baby with red hair and a blue shirt. The way to solve this problem is to have search engines be able to detect the content of the video using image recognition. This works today with things like human faces but other objects take a lot of effort to categorize them.
Here’s an article about a breakthrough in improving this process. (H/T BYU)
BYU engineer Dah-Jye Lee isn’t interested in that development, but he has managed to eliminate the need for humans in the field of object recognition. Lee has created an algorithm that can accurately identify objects in images or video sequences without human calibration.
“It’s very comparable to other object recognition algorithms for accuracy, but, we don’t need humans to be involved,” Lee said. “You don’t have to reinvent the wheel each time. You just run it.”
That last part is very significant. Automating this process is very important to deal with the massive amount of data on the net. It will allow companies like Google to add video and image content to their indexes and increase the amount of searchable information by many orders of magnitude.
The other field this really helps with is Augmented Reality. Having a camera on your glasses coupled with this technology will allow the glasses to automatically understand what is around you.
Watch for Google to hire this guy. 🙂