Recent research has seen exciting updates in age identification, from huge databases of age information to vending machines that can guess a customer’s age. Now, a new algorithm created by researchers at A*STAR Institution for Infocomm Research, could make age identification cheaper and easier to incorporate into machines.
In most age-identification research, machines are trained to recognize age by analyzing massive databases of information and learning from mistakes. But this approach has many downsides, including its time and monetary expense, as well as the possibility of breaching privacy laws for using unauthorized photographs of people.
The new method from A*STAR, called incremental bilateral two-dimensional linear discriminant analysis (IB2DLDA), avoids these downsides by actively learning about age information.
First, the tool analyzes a small set of labeled images of human faces. Using information gathered from these images, it then chooses from a pool of unlabeled pictures the most informative images. According to the researchers, informative pictures in the unlabeled set tend to be very different from the pictures processed from the labeled set.
According to lead researcher Jian-Gang Wang, this “active learning” approach requires fewer sample images and less time to develop an accurate age-identification system.
In tests, the researchers demonstrated the their algorithm is much faster and requires fewer sample photographs than the random selection used by other age-identification systems. The team thinks its tool could also be expanded to identify other facial aspects. “We are now planning to extend our method to other areas such as classifying human emotions and actions,” said Wang, according to a statement.
This simpler and cheaper method of age identification might make it easier to incorporate the technology into machines and other tools. Possible applications include smart billboards, which choose ads based on the age of the audience.
“A vending machine that can estimate the age of a buyer could be useful for products that involve age control,” said Wang, “such as alcoholic drinks and cigarettes.”
The research was recently published in IEEE Transactions on Image Processing. Click here to read more about the new technology.

Good morning from Los Angeles! #ibmcloud
That's it from me! Over to North America.
The data processing of Roland Garros 2012 (#RG12) rests on IBM Private Cloud http://t.co/JUaY1ItM [French Press release]
IBM Accelerates Business from Supply to Demand with New #Cloud Offerings For Smarter Commerce http://t.co/OFxknOb0 [Press Release]
How IBM #SmartCloud Foundation technology powers cloud adoption?
IBM VP @SLHebner explains here http://t.co/sSzfa0O5 [VIDEO]
IBM's Fiona Cullen will present ‘The Power of #Cloud: Driving Business Model’ On May 24 @ Utrecht, Netherlands #cloudforum2012 #ibmcloud
Blog Post: Why service providers should not ignore cloud http://t.co/ZfQyue4r via @eMarcusNet #thoughtsoncloud
Have any #cloudmoment? Share your story with us via Twitter, Instagram, YouTube, Facebook and tag it. See other stories http://t.co/J4ntsaQ5
Sign up now for IBM #SmartCloud Enterprise! No charge for select VMs (only till May 28). More Details >> http://t.co/2LEzOUZC #ibmcloud
RT @HansMoen: See this video from @IBMCloud to learn how to cut costs in building innovation in your business http://t.co/XOyJoFn6 #clou ...