Google unveiled a prototype algorithm at a conference in Beijing last week that will add precision to the search engine’s image-search technology, The New York Times says.
Two Google researchers presented a paper describing the prototype, which is called VisualRank. It uses image-recognition technology to help rank the relevance of images found in a search.
Currently, Google Image Search results are ranked using the text around the image on the page. The new method will use the visual characteristics of the image itself, and rank search results by comparing similarities among them. —Hurley Goodall
4 Responses to A Research Paper Introduces Better Google Image-Search Technology
22086364 - November 30, 2011 at 7:04 am
Yes! Another parallel I have found in about 33 years of running and 22 years teaching, is that both sometimes get messy, and you end up with a suffer-fest. Ultimately, finishing the run or race is usually worthwhile, and finding ways to be still more effective as a teacher is ALWAYS worth the angst, insecurity, and even vomiting.
Nice article. Best wishes in the Indy training and race.
andrewsj - November 30, 2011 at 9:49 am
Very nice. As a long term, but now former, runner and as only an occasional teacher, this spoke to me on many levels. Thanks, and good luck on that half.
smtan - November 30, 2011 at 11:48 am
I too just started running this year. The hardest part in both running and teaching is right before the beginning when you wonder if you will make it, and the best is when you hit that “groove” and the mile/semester just flies by.
karold - December 5, 2011 at 9:38 pm
thank you for sharing your running, good luck! http://www.baileybuttonbootsau.com/