By Vikram Sethi
Computers can mimic the human ability to find visually similar images, such as photographs of a fountain in summer and in winter, or a photograph and a painting of the same cathedral, by analyzing the uniqueness of images, say researchers at Carnegie Mellon University’s School of Computer Science.
The research team computes uniqueness based on a very large data set of randomly selected images. Features that are unique are those that best discriminate one image from the rest of the random images. (In a photo of a person in front of the Arc de Triomphe in Paris, for instance, the person likely is similar to people in other photos and thus would be given little weight in calculating uniqueness. The Arc itself, however, would be given greater weight because few photos include anything like it.)
The research team, led by Alexei Efros, associate professor of computer science and robotics, and Abhinav Gupta, assistant research professor of robotics, found that their technique performed well on a number of visual tasks that normally stump computers, including matching sketches of automobiles with photographs of cars. Their research paper is available online.