Google has shown us this morning its winning entry that was entered in an annual computer vision challenge. Those who've entered include industry labs and academic institutions. Google has also made its work available to other researchers.
“In this year’s challenge, team GoogLeNet tasks, doubling the quality on both tasks over last year’s results. The team participated with an open submission, meaning that the exact details of its approach are shared with the wider computer vision community to foster collaboration and accelerate progress in the field…”
Google's self-driving cars is one of the directions the search giant will go in with the technology among apps like YouTube and photo/image search.
“These technological advances will enable even better image understanding on our side and the progress is directly transferable to Google products such as photo search, image search, YouTube, self-driving cars, and any place where it is useful to understand what is in an image as well as where things are.”
What other applications this could be used in, is yet to be determined, but one suggested application involves robotics. Even so, the idea of improved image recognition is enough to make this blogger happy.
source: Google Research Blog
via: 9 to 5 Google
