By modifying a common type of machine-learning technique, researchers have found a better way to identify pictures.
Finding photos: A new algorithm developed at UCSD that adds word tags to images can increase image-search accuracy and efficiency. Above, features from a picture are assigned a likelihood that they belong in certain categories, such as “water” or “person.” Credit: Gustavo Carneiro, Antoni B. Chan, Pedro J. Moreno, and Nuno Vasconcelos
Researchers at the University of California, San Diego (UCSD), have developed a new image-search method that they claim outperforms existing approaches "by a significant margin" in terms of accuracy and efficiency.
The researchers' approach modifies a typical machine-learning method used to train computers to recognize images, says Nuno Vasconcelos, professor of electrical and computer engineering at UCSD.
The result is a search engine that automatically labels pictures with the names of the objects in it, such as "radish," "umbrella," or "swimmer." And because the approach uses words to label and classify parts of pictures, it lends itself nicely to typical keyword searches that people perform on the Web, says Vasconcelos.
...
For instance, consider submitting an image of a dog on a lawn. The objects in the pictures are analyzed and compared with results for known categories of objects, such as dogs, cats, or fish. Then the computer provides a statistical analysis that gives the likelihood that a picture matches those categories.
The system might score the picture with a 60 percent probability that the main object is a dog and a 20 percent probability that it is a cat or a fish. Thus, the computer deems that, in all likelihood, the picture contains an image of a dog. "The key idea is to represent images in this semantic space," Moreno says. "This seems to improve performance significantly."
Source : http://www.technologyreview.com/Infotech/18501/page1/
No comments:
Post a Comment