Yesterday, New Scientist put out a report that Google was funding the development of an app called InSight for Glass, which would recognise people based on their clothing and not their actual faces. After some head-scratching about why anyone would need such an app — and I scratched a lot of people's heads about this — it turns out that the report was a little misleading.
But first, what is InSight, you ask? It's, well, this, according to the abstract:
Wearable cameras and displays, such as the Google Glass, are around the corner. This paper explores techniques that jointly leverage camera-enabled glasses and smartphones to recognise individuals in the visual surrounding. While face recognition would be one approach to this problem, we believe that it may not be always possible to see a person's face. Our technique is complementary to face recognition, and exploits the intuition that colours of clothes, decorations, and even human motion patterns, can together make up a "ﬁngerprint". When leveraged systematically, it may be feasible to recognise individuals with reasonable consistency.
So was InSight built with the intent of being an app for Google Glass? When I asked Srihari Nelakuditi — an associate professor at the University of South Carolina who is part of the InSight team— about this being an app for Glass, he had this to say, "Actually, that's not true. We don't have Google Glass. We haven't done anything with Glass."
But the team did simulate a Glass-like situation by combining an Android phone with PivotHead's camera-enabled shades for testing purposes. So I can see why many folks think this is an app for Glass. Except it's not.
Also, Google isn't really funding the project, at least not in the traditional VC way. Nelakuditi tells me that he and his colleagues from Duke University (He Wang, Xuan Bao and Romit Roy Choudhury) have been working on this for about six months and decided to apply for a Google Faculty Research Award. They won. See here and here.
So how and when would someone actually use this? Nelakuditi says it's meant for situations where you might be looking to hitch a ride back from a conference or when you're trying to hawk an extra ticket outside a theatre or stadium and need a visual cue for others to acknowledge. Which is maybe not all that practical when thinking about Glass in particular.
More to the point, a lot of folks jumped on this story because it contained "Google Glass" somewhere in the headline or copy. And as much as we all want to expound on Glass now, we really have no idea what developers and Google are working on outside of the most obvious use cases. Realistically, Glass isn't a thing that exists yet. Think of all the concepts we never see or notice being used around us. Glass shouldn't be any different. And until we get real details from Google — and developers have had real time with it — we're all just flying blind.