Software recognizes and describes images in words |
U.S. researchers have developed a computer system that can automatically recognize the content of a photograph and describe it in English.
The technology makes it possible to automatically tag images with keywords, rather than having a person manually label the photos. The system can tag online collections of images as they are uploaded
"By inputting tens of thousands of images, we have trained computers to recognize certain objects and concepts and automatically annotate those new or unseen images," Wang said in a statement. "More than half the time, the computer's first tag out of the top 15 tags is correct."
http://www.cbc.ca/technology/story/2006/11/02/tech-imagetag-061101.html#skip300x250
The ALIPR (pronounced a-lip-er) system, launched on November 1, 2006, is being developed at Penn State by Professors Jia Li and James Z. Wang. For more information, contact them by email at jiali at psu.edu and jwang at psu.edu, and by phone at +1-814-863-3074 for Jia and +1-814-865-7889 for James. They started their work as early as in 1995 while they were both with the Stanford University, where the Yahoo! and Google projects were started by their fellow schoolmates. Different from these successfull projects, Li and Wang attempted to develop computer systems to manage millions of images by the pixel content.
http://www.alipr.com/about.html
I submitted this image (by Fotosmurf) to reconize the content
The result:
animal, grass, landscape, dog, bird, building, historical, wild_life, flower,lake,everglade, horse, people, rural
Wow! I would doubt only "dog"...:)
Link to try | Also please review an article about a different approach of describing images in words by Researchers at the University of California, San Diego (UCSD) |
|