Image Search, People Tagging and Skunk Works
As Chief Business Architect the best part of my job is that I have a lot of room to run out in front of the execution / operation team to spend money and to do things that the company otherwise wouldn’t do. I recently hired a new developer to the team, Semi Mol, who will be assisting me in a new “Skunk Works” project. While I obviously can’t get into what exactly we’ll be collaborating on I can tell you that it’s going back to the core of the Tagcow dream. When Matt and I conceived the idea for Tagcow over Sushi in December of 2007 we had one big idea - searching your personal image archive would be cool. Since then we’ve drifted away from the consumer image tagging market and moved towards the Enterprise market because getting a few companies to write big checks is easier than getting millions of consumers to write you small checks.
While we’ve been off busy executing on our Enterprise strategy I kind of figured that with all the noise being generated out of Facebook, Flickr, Photobucket and others that somehow this problem was well on its way to being solved but then I looked a little closer…and you know what? All the noise was really around “People Tagging” either manually or through facial recognition software and honestly it’s not that interesting. It’s fundamental but not game changing. I’d recommend Face.com’s facial recognition software any day and if I had some spare time I’d call those guys and integrate their software into our platform to help with people tagging. But the real heart of the tagging opportunity lies with “descriptive tagging” of images which no one does better than Tagcow. So you have 400 photos of your daughter, Novella, tagged now what? It’s the ability to narrow down your results to “Novella + ballet” or “Novella + laughing” that’s really interesting.
As Semi and I make progress on this front I will keep the blog updated.
Welcome to the team Semi, it’s going to be a wild ride 
 |
| Semi Mol |
Tags: image search, image tagging, people tagging