Search for Your Face Online

MoreVisibility - December 27, 2006

I admit it; I love the TV show “Vegas”. One of the things I always found fascinating in that show was the facial recognition tool they use in the security room. It is great the way they scan through a database of faces and find a match to someone they just video capped from the security cameras. It’s basically a search engine for faces.

What if everyone had access to this database, what if you could search for a face online or even the opposite, find a face and click it to get detailed info on who it is. Well, you’re not going to have to wait long. A new search plug-in coming from Polar Rose will allow you to do just those types of searches.

The plug-in is due to be launched in beta during the first quarter of 2007 and will be available for both FireFox and Internet Explorer. According to Polar Rose, you will be able to click on a persons face and find out who they are and some data about them or enter a name and see a collection of photos of the person. They claim it will work on any photograph publicly available online. I can already imagine the outcries of the security zealots out there, but that is a topic for another article.

Looking at the big picture however, I think challenging the basic notion of how search works is the most interesting aspect of this new tool.

Apart from the change from textual to visual, there are a couple of other not so obvious factors which make this different in terms of search. First, it is a plug-in. While we have had plug-ins to help us with searching before, this is a bit different. This plug-in allows you to directly interact with the content on a page and search for specific info related to that content without even leaving the page.

Second, the data which drives this visual search tool will come from two distinct sources. Their website states “Polar Rose relies on a combination of our unique face recognition algorithms and the collective intelligence of our users.” Basically, along with their facial recognition algorithms, they will add a social element which allows users to add information about images to be applied to the image data. This idea of incorporating user generated content and social media directly into the search process may become even more integrated in the future.

I guess my point here is that search is changing. Yes it is still very early in the game, but compared to today, search models in the next decade could be as different as rotary dial phones and smart phones. It is possible that in 2017, people will think about the current text/keyword based search model as “old school”. Be prepared for changes in search and keep your sites and surfing habits up to date. You don’t want to be left behind on either one.