Thanks to Scoble, I’m clued into the latest, geekest development onthe web. google introduced the much refineed version of searching that is synonomous wiht, well, search. Google’s oversight was that it searched text (ie. filenames, titles, etc). Even the image search.
Like.com, however, searches the image itself for other similar items. For an alpha release its increbibly sophisticated, allowing you to fine tune the search according to color, shape and pattern You can choose the color you want. You can also toggle how important each charecteristic of the item is for your search.
This will do wonders for my bank balance. And the simple reason is: it works. While tags do go a certain way to describing an item, article ir webpage, the visual aspect is far more powerful. They say a picture is worth a thousand words – this proves it.
The facinating part of all this is that back end. Exactly what software its running on i’m not sure. but the hardware is impressive enough. 250 servers with 4 processors each and 20 gigs of RAM. While the number of categories you can search may seem rather samll compared to the hardware arrayed for the task, using like.com and seeing its sophistication makes you see why.
I’d love to see the code for this ;). Something tells me thats not gonna happen.
The idea is simple, buy mudersly complex in exectution. I’m not into image manipulation this far in my course, but getting the computer to think is a big enough job.
I hope the set of seaches expands in the near future. They are tweaking and testing and trying to wring every extra processor cycle out of the program. I know the drill.
I just hope that a web service comes out of this. I already have an idea. Combine like.com with google maps ( or Windows Live Local) to show the nearest store you can buy the item from. That would be cool.
Anyway Scoble has a few titbits:
Some stories about Like.com.
1) The URL cost him $100,000. In the interview he explains how they bought it. It involved finding the guy who owned it, jumping a fence, and leaving a bottle of wine with a note on it (he wouldn’t answer his email).
2) Riya was pretty close to being sold to Google. If it had been, they never would have worked on this search engine. So, by getting turned down by Google Riya came back with a much better business.
3) Just the jewelry set takes 20GB of RAM.
4) Munjal still believes in blogs, but for this launch Riya talked with fashion bloggers, and journalists outside the tech world like at People magazine. Why? Well, this site — in its current incarnation — will be most interesting to women and non-geeks. If you’ve looked at who participates here, it’s heavily male.
5) Why not keep working on face detection? Because they learned through user testing that they’d never be able to make it good enough. They found that by focusing on visual image searches they can get a much more satisfied user base.
Random Musings 