Thumbnail images provide image retrieval and browsing systems users with a method for quickly scanning large numbers of images. Recognizing the objects in an image is important in many retrieval tasks, but thumbnails generated by shrinking the original images often render objects illegible.
Researchers at the University of Maryland, College Park, have developed code and methods allowing for the detection of salient portions of images and for automatic face detection so that small thumbnails can be generated based on cropping to show those salient portions. The automatically generated thumbnails are more recognizable and easier to find in the context of a visual search. This technology could be useful for any image browsing system where space is of the essence - such as when there are many images or limited display space.
Code and methods are available on a non-exclusive basis. Please contact the Office of Technology Commercialization at the University of Maryland for addition licensing information: Jim Poulos at 301.403.2711 ext. 20 or by e-mail, jpoulos@umd.edu. |
