Hasta La Gadget!

Google Glass use cases are many, but one that inevitably comes to mind is facial recognition. Google already does a lot with reverse image searching and identifying faces in photos, so it would not be such a leap to imagine it doing something like comparing the faces of those you meet at networking events to publicly available photos from Google+ and other sources to make sure you never again forget a name. But Google has forbidden that kind of software in the official Glassware app store. Still, startup Lambda Labs and its founder Stephen Balaban are building that software anyway, for installation via sideloading.

That workaround means the app, called FaceRec, will only ever make it onto a fraction of Glass devices, and a Google spokesperson had this to say when contacted for comment as confirmation it’ll never get broad distribution through any official channels:

As our Glass Developer Policies make clear, we will not be approving any Facial Recognition Glassware.

A subset of the Explorer crop can’t add up to many installs, but that’s exactly who it’s intended for, Lambda tells Forbes. The app works by storing a record of every face that a user encounters while wearing glass, on a cycle that refreshes to capture new faces every ten seconds. In this early version, it can’t ID faces in real-time, and doesn’t have a reference database from which to draw. Instead, like with iPhoto and other services, you can tag pictures with names so that they’ll be recognized the next time you see them. Users can also roll their own script for mining data from their Facebook network for automatic identification, but it’s not built into the product since it violates Facebook’s rules of usage.

The first version of Lambda’s Glass facial recognition app might be limited, but it’s a first step to something more on par with what we might expect from sci-fi examples, where you glance at someone and get a profile of them, shared interests and more provided via a heads-up display. Which is great, because getting to know people the old fashioned way through conversation and a gradual deepening of mutual understanding is for the birds.

Seriously though, there does seem to be a general level of anxiety around the idea of Google Glass and facial recognition. But over time we’ve proven ourselves to be quite changeable on the definition of what is and isn’t acceptable when it comes to how much information we share with others via the web, and facial recognition could become something that people grow more comfortable with time. It definitely has a range of positive possible use cases, including for treatment of genuine medical conditions like prosopagnosia or the aftermath of strokes.

Google may eventually relax its privacy restrictions to make this kind of app officially supported on its Glass platform, but Lambda is also building its own Android-based wearable device called the “Lambda Hat” that will be available for pre-orders Friday. This and other platforms developed outside of Google likely won’t carry similar strictures about face recognition tech, so Balaban’s concept of a world where we can know people just by looking using computer vision might come to pass regardless of Google’s reservations, and the serious privacy implications such a concept entails.

This may be a particularly interesting example of unauthorized Glass software, but software outside the bounds of platform restrictions is nothing new. Apple has a far-reaching and active iOS jailbreak community, after all, and Android devs have created many apps that can be sideloaded but don’t make it into the Play Store. Glass is bound to play host to a few of those as well, but novel technology makes for novel takes on what constitutes ‘out-of-bounds’ software. None of these unauthorized apps really make it beyond outlier or curiosity status, unless policies change and they gain access to official channels, but they can still be worth watching as barometers of what users find interesting and/or acceptable in specific examples of mobile software.

Russian search giant Yandex has collaborated on developing an experimental gesture-based interface to explore how similar technology could be incorporated into future social apps and mobile products. The company offers digital services beyond search already, launching and expanding mapping services and translation apps, for instance, in a bid to drive growth as its domestic search share (60.5% as of Q4 2012) has not grown significantly in recent quarters. Future business growth for Yandex looks likely to depend on its ability to produce a pipeline of innovative products and services — hence its dabbling with gestures.

Yandex Labs, the division that came up with its voice-powered social search app Wonder (an app that was quickly blocked by Facebook), has been working with Carnegie Mellon University on a research project to create a gesture-based social interface designed for an Internet-connected TV. The interface, demoed in the above video, pulls in data from Facebook, Instagram and Foursquare to display personalised content that is navigated by the TV viewer from the comfort of their armchair using a range of hand gestures.

Here’s how Yandex describes the app on its blog:

The application features videos, music, photos and news shared by the user’s friends on social networks in a silent ‘screen saver’ mode. As soon as the user notices something interesting on the TV screen, they can easily play, open or interact with the current media object using hand gestures. For example, they can swipe their hand horizontally to flip through featured content, push a “magnetic button” to play music or video, move hands apart to open a news story for reading and then swipe vertically to scroll through it.

The app, which was built on a Mac OS X platform using Microsoft’s Kinect peripheral for gesture recognition, remains a prototype/research project, with no plans to make it into a commercial product. But Yandex is clearly probing the potential of gestures to power future apps.

Asked what sort of applications it believes could be suitable for the tech, Grigory Bakunov, Director of Technologies at Yandex, said mobile apps are a key focus. “Almost any [Yandex services] that are available on mobiles now: search (to interact with search results, to switch between different search verticals, like search in pictures/video/music), probably maps apps and so forth [could incorporate a gesture-based interface],” he told TechCrunch when asked which of its applications might benefit from the research.

Bakunov stressed these suggestions are not concrete plans as yet — just “possible” developments as it figures out how gesture interfaces can be incorporated into its suite of services in future. ”We chose social newsfeeds to test the system [demoed in the video] as it can bring different types of content on TV screen like music listened by friends, photo they shared or just status updates. Good way to check all types in one app,” he added.

As well as researching the potential use-cases for gesture interfaces, Yandex also wanted to investigate alternatives to using Microsoft’s proprietary Kinect technology.

“Microsoft Kinect has its own gesture system and machine learning behind it. But the problem is that if you want to use it for other, non-Microsoft products you should license it (and it costs quite a lot), plus it has been controlling by Microsoft fully. So, one of the target was to find out more opened alternative with accessible APIs, better features and more cost-effective,” said Bakunov.

Yandex worked with Carnegie Mellon students and Professor Ian Lane to train gesture recognition and evaluate several machine learning techniques, including Neural Networks, Hidden Markov Models and Support Vector Machines — with the latter technique showing accuracy improvements of a fifth vs the other evaluated systems, according to Yandex.

The blog adds:

They [students] put a lot of effort in building a real training set – they collected 1,500 gesture recordings, each gesture sequenced into 90 frames, and manually labeled from 4,500 to 5,600 examples of each gesture. By limiting the number of gestures to be recognized at any given moment and taking into account the current type of content, the students were able to significantly improve the gesture recognition rate.