Gazopa, a search engine that uses features from an image to retrieve similar images, has been in private beta since it launched during TechCrunch50 last year. To recap, Gazopa lets users upload a picture, enter a URL of an image, create a drawing or right-click on an image anywhere on the web (via a plug-in) and retrieves similar images. A thumbnail of a video is enough to look for similar videos.
Results are mainly filtered through analyzing the color and shape of the object or person pictured. Upload a picture of a red car, for example, and Gazopa will find pictures of similar cars on the web – without you having to type any keywords (search via keywords is also possible though).
Since September 2008, more than 40,000 users have tested the service, which entered open beta today. And Hitachi America, the company behind Gazopa, has used customer feedback to improve the quality of search results, tweak the site’s design and add a number of features in the past year.
One of the most notable additions is the Gazopa iPhone app (iTunes link), which is pretty cool and lets you take and upload photos with your iPhone to quickly get similar images off the web. The app has all of the main features of the web version and is free. There’s also a new Gazopa Drawing Facebook application.
Gazopa now allows users to browse through Flickr images and filter out those without a Creative Commons license. When you hover over a particular image, Gazopa will show you its size, how similar it is to the one the search is based upon, licensing details and a URL that will take you the picture’s Flickr page. Another new feature is the news tab under which users can find images related to the latest news. Those images can be filtered by time (uploaded within one month, a year etc.), shape and size.
Granted these aren’t earth-shattering new features, but GazoPa has indexed over 60 million images so far that can be searched even if they have no or inaccurate meta data. The open beta version is still a bit buggy but more than OK for a test run. One major point that leaves room for improvement is that searching for inanimate objects with distinctive features seems to lead to significantly better results than searching for human beings that look similar. It would be nice if Gazopa could at least distinguish between men and women, for example, which isn’t always the case.
Asked what differentiates his service from Google Labs’ similar search service, Gazopa project leader Hideki Kobayashi said that Google doesn’t let users find similar images of all images displayed and that uploading a picture by yourself isn’t possible. Gazopa also competes with “reverse image search engine” TinEye, which, however, doesn’t necessarily look for “similar” images but tries to find exact matches of pictures instead.
Here’s a demo video for Gazopa’s open beta version:
Screenshots:
Great idea but possibly the worst name I’ve ever heard
Dude what took them so long?
Going to try it out soon..
That’s just excellent…. Perfect results…
Might Google will acquire them… as they are also working on similar lines….
Am sure this kind of service will get better over time, but my first brush with it isn’t exactly inspiring.
I tried a couple of different photos of mine. In this one, it thinks I look like Steven Spielberg or David Archuleta, a contestant from American Idol or prime minister Gordon Brown or…:
http://ow.ly/i/50R
Ok, I thought, it might be because of the fact that it’s more of a profile view than a straight-on-the-camera view. But here’s what happened when I tried something more straightforward:
http://ow.ly/i/50W
Sigh.
Reminds me of another service that allowed you to see if you look like someone famous: http://www.saja...y_experime.html (at least they got the ethnicity right!)
They think Manmohan Singh looks like Steve Ballmer!
@raakshas: hilarious! for those not familiar with mr. singh, he’s india’s prime minister, a sikh gentleman with turban, white beard, etc.
tried, uploaded an image and wanted to find same/similar images, but none of the results were the image i uploaded.
why have not u mentioned TinEye as competitor?
ok sorry, u have mentioned tineye, my bad.
I think gazopa has teh potential to beat google similar image project given that facebook and iPhone app succed in doing what they are supposed to do
watch the complete video review of Gazopa here with more of the iPhone app
http://thetechn...d-video-review/
Looks awesome, very useful
Idea is good.. But the results are not accurate.
Just search for the ‘Horse racing’ image on the home page.
http://www.gazo..._576_090926.jpg
It shows a lot of results. The second image not much similar, but the result says, 61.44% similar.
The third image is almost similar to the searched image, but the result says 61.38% similar.
The results need to be still more accurate.
this engine is hallarious…
i uploaded the picture of a simple elephant (simple because there was no clutter in the picture and the elephant shape was clear).. and it game me pictures of women’s faces… when i looked for similar pictures to some of those women’s faces… it showed me more elephants 
it’s almost worth paying for such entertainment 
Deja vu, Just replace the logo and we have the exact same site and layout as google no?
This is Ridiculous! I searched using a picture of ranch house, and its bringing up a pic of beaver, baseball player, the freakin Taj Mahal! Its an interesting concept, but they have ways to go. Best of Luck!
Awful name, bad logo aka Google parody, not impressive results and not usable UI. What else?
i just tried it out with a pic of myself wearing a blue hat. a whole of of faces came up. none with hats
but i did get
- doctor leonard mcKoy
- george W bush
- and some underwear model
it was entertaining at least.
Interesting, but it relies too much on color similarity. This concept is very cool, but I don’t know if the general public will care about this sort of feature as-is. I think the real power here is if they open it up as a platform and let people build applications on top. I would love to have a feature like this at Twicsy, and I could see lots of other sites would like something similar, really just about any site that sells things where people post pictures (ebay, craigslist, etsy, etc.).
I remember this at an IBM Research lab in San Jose back in 1996.
It uses Color Placement for search… that’s all.
You need to add context otherwise anything that has the same colors in the same place will come up.
Upload a tan color band-aid at a 45 degree angle, get a tube of tan color make-up at a 45 degree angle.