SOMEWHAT FRANK

Polar Rose Puts A Name With A Face

Putting a name with a face can sometimes be a rather taunting task in public. However, online Polar Rose is looking to help solve this problem by leveraging facial recognition technology and the power of people online.

Xcavator.net For Stock Image Recognition & Color Search

Are you looking for a solid image search? xcavator might be able to help as it offers a couple of interesting image search options. Unlike other image search engines, xcavator enables users to search stock images by selecting an image color, tag or keyword.

Using an innovative color selector users can find images with a similar dominant color. The color selected can then be filtered by tag or keyword. Users can search among royalty free and licensed images. Additionally, xcavator uses image recognition technology which was created by CogniSign to allow users to search on an uploaded image. Check out the video tour here - a screen-shot of a simple color search is shown below.

Find Your Celebrity Look-Alike

Editor's Note: If you like my insights and perspective in this article please join my inner circle here.

Which celebrities do you look like? AOL may be able to help answer that question with its recent launch of an innovative facial recognition technology, similar to that of Riya and MyHeritage, created by AOL Labs in collaboration with Oxford University and Caltech University. Thus far the technology has been used in a fun little site called FindMyCelebrityLookAlike.com. AOL Labs is the technology research group of AOL responsible for delivering insight and capabilities to build the next generation of services for the company. 

By submitting a photo by either uploading an image or by submitting an URL to the photo you can search celebrities for a match. Users can tweak the search results by limiting them to a particular gender. In addition, users can find additional information about the celebrities that they look like. So find out who you look like. I decided to look for both male and female results and turns out I look like singer Jesse McCartney, actor Elijah Wood, actress Keira Knightley and actor Adam Brody. What do you think about the results? I am kind of close to the situation so it is difficult for me to judge.

If you like my insights and perspective in this article please join my inner circle here.

Mobot First Mobile Visual Search Engine

Have you ever seen something in a store or while reading a magazine that you want to remember so you take a photo of it with your cellphone camera?

Mobot is a startup that plans to leverage this type of mobile phone behavior to offer an innovative service. Mobot is the first ever mobile visual search. Similar to online visual searches Like.com a byproduct of Riya, Mobot searches for items based on an image that is taken with with a mobile device. It appears that Mobot has partnerships with certain products and services and thus when you submit an image Mobot serves up relevant products and services. Without actually being able to test the service it is difficult to determine the relevance and accuracy of the search functionality. However, it appears that most U.S. cellular carriers will carry Mobot so I should be able to test it when it does actually become available.

Additional details are sure to come once Mobot makes its move to market but in the meantime check out more information on Mobot technology.

Bottom-line: Mobot is the first mobile visual search which could be a helpful service as long as it doesn't go overboard with promotional results but delivers accurate and relevant search results.

Like.com: Leverages Image Recognition Search For Online Shopping

Like.com, a product created by Riya, launched today (November 8, 2006) to offer what appears to be the first visual image recognition search engine in a consumer facing application. The site offers the ability to search by photos to identify similar items. Like.com applies this functionality to shopping to help shoppers to find items like shoes, watches, and handbags. Like.com could really help the loads of celebrate crazed, "I gotta have one if they have one" types find just what they are looking for online. For example, take this photo below of Mike Arrington sporting a sweet watch at the ONA conference in Washington, DC. Soon, you will be able to use Like.com to be Mike.

On the Like.com site a highlighted area which contains an item, in the photo above a watch, returns similar watch search results. Currently, Like.com does not offer Mike Arrington photos for search though but you can search for items worn by other celebrities. Within the next month Like.com will let users submit photo uploads to apply the same type of technology.

How does Like.com do it? Like.com applies learnings from photo recognition site Riya to enable Like.com to converts each image into variables that map to contextual meta-data which is then used to perform the search to match shape, texture and a number of other characteristics.

TechCrunch recently provided more information and some videos here.

Bottom-line: Sounds pretty innovate, not to mention helpful in finding a similar watch as Mike Arrington.