Three year old children can make sense of what they see in photos and describe them to us, but even the most advanced computers have historically had difficulties with that same task. That’s quickly changing though, as computer scientists are developing powerful new ways to have computers identify what a photograph is showing.
The video above is a new TED talk given by Fei-Fei Li, a Stanford professor who’s one of the world’s leading experts on computer vision. She talks about her revolutionary ImageNet project that has changed how computers “see.” Read more…
When a beta version of Apple’s iOS software is released, you can bet developers are sifting through the code like mad to see if any new features have been added to the mobile operating system.
It would appear as if hidden in the code for iOS 7 beta 2 are camera-oriented features for use by developers. One feature apparently detects smiling in photos, the other detects blinking. These detectors may hint at features coming to the iPhone, iPod, and iPad cameras in the future. Read more…
In this day and age, you’re likely to have a hard time walking down the street and not seeing a camera somewhere. If it isn’t held by the shutter-happy tourist in short shorts, it’s the CCTV camera mounted at the entrance of the local subway station.
How does one maintain anonymity? Staying in? No! You put on fabulous privacy-protecting glasses under development by Japan’s National Institute of Informatics. Read more…
Cameras these days are smart enough to recognize the faces found inside photographs and label them with names. What if the same kind of recognition could be done for the locations of photographs? What if, instead of using satellite geodata, the camera could simply recognize where it is by the contents of the photographs?
That’s what research being done at Carnegie Mellon University and INRIA/Ecole Normale Supérieure in Paris may one day lead to. A group of researchers have created a computer program that can identify the distinctive architectural elements of major cities by processing street-level photos. Read more…
Facial recognition technology has become ubiquitous in recent years, being found in everything from the latest compact camera to websites like Facebook. The same may soon be said about location recognition. Through a new project called “Finder“, the US government military research division IARPA is looking into how to quickly and automatically identify where a photograph was taken without any geotag data. The goal is to use only the identifying features found in the background of scenes to determine the location — kinda like facial recognition except for landscapes.
Google has acquired UK-based mobile photo search startup Plink for an undisclosed amount.
The company’s sole product Plink Art is an Android application that allows you to look up information about a piece of art by simply photographing it with your phone.
The application was one of the winners of Android Developer Challenge 2, scoring a $100,000 prize for winning in the “Education/Reference” category.
Remind you anything?
Artwork recognition is one of the features offered by Google Goggles, which is what Plink’s founders will be working on at Google.
Since the Plink only has 50,000 users, this is mostly a talent acquisition to improve Google’s visual search technologies.
The announcement posted to Plink’s blog gives a glimpse into where Google would like to go with visual search:
The visual search engines of today can do some pretty cool things, but they still have a long long way to go. We’re looking forward to helping the Goggles team build a visual search engine that works not just for paintings or book covers, but for everything you see around you. There are beautiful things to be done with computer vision – it’s going to be a lot of fun!
Imagine a world where you can “Google” information about anything by aiming your cell phone at it and snapping a picture.