[ad_1]
Researchers, including those of Indian-origin, have developed a new program that helps computers learn common sense through pictures, enabling them to scour the internet and label images on their own.
The computer program can make associations between things to obtain common sense information that people just seem to know without ever saying – that cars are often found on roads, that buildings tend to be vertical and that ducks look sort of like geese.
The computer program called the Never Ending Image Learner (NEIL) is running 24 hours a day at Carnegie Mellon University, searching the Web for images, doing its best to understand them on its own and, as it builds a growing visual database, gathering common sense on a massive scale.
NEIL leverages recent advances in computer vision that enable computer programs to identify and label objects in images, to characterize scenes and to recognize attributes, such as colors, lighting and materials, all with a minimum of human supervision.
In turn, the data it generates will further enhance the ability of computers to understand the visual world.
Based on textual references, it might seem that the color associated with sheep is black, but people – and NEIL – nonetheless know that sheep are typically white.
“Images are the best way to learn visual properties,” said Abhinav Gupta, assistant research professor at Carnegie Mellon’s Robotics Institute.
“Images also include a lot of common sense information about the world. People learn this by themselves and, with NEIL, we hope that computers will do so as well,” said Gupta.
A computer cluster has been running the NEIL program since late July and has already analyzed three million images, identifying 1,500 types of objects in half a million images and 1,200 types of scenes in hundreds of thousands of images.
[ad_2]