GazoPa's Similar Image Search

I loved the GazoPa demo on the TechCrunch50 stage. They referred to it as "similar image search." Users can search images from the web based on user’s own photo, drawings, images found on the web and keywords. GazoPa enables users to search for a similar image from characteristics such as a color or a shape extracted from an image itself.

On stage, they searched for similar like images of objects like purses/handbags and food, i.e., pizza for example. When he clicked on a purse, it would then return a bunch of like-purses that had similar shapes or colors.

You can also do a search using a drawing. In this example, he drew a t-shirt and up came photos of t-shirts that you could browse. Then we saw a 'face search,' where he used President Bush as his example. When he right clicked on Bush, it showed other Bush images on the web.

There are abundant quantities of images on the web, however many of these simply cannot be described by keywords. Since GazoPa uses image features to search other similar images, a vast range of images can be retrieved from the web. GazoPa is a new visual search service that can navigate users to new territories on the web.

Hitachi is the backbone behind it apparently and it is going into private beta this week.