"The team found that its programme not only did a better job of matching features of parents and their kids than random chance, but it also outperformed existing software for identifying relatives through photos by three to 10 percent."
New York, June 20 - A new facial recognition computer tool can help a missing child meet his/her parents by rapidly and accurately matching pictures with their biological parents.

We wanted to see whether a machine could answer questions, such as 'Do children resemble their parents' or 'what parts of the face are more genetically inspired', said lead researcher Afshin Dehfghan from University of Central Florida (UCF).

The new tool is able to focus on indicators people may not find as significant - such as the left eye, the chin and parts of the forehead.

By designing an algorithm to focus on specific features, the research team converted the photos into a checkerboard of patches and extracted tiny snapshots of the most significant facial parts.

The tool compared all the photos feature by feature and sorted them by the most probable match.

The team found that its programme not only did a better job of matching features of parents and their kids than random chance, but it also outperformed existing software for identifying relatives through photos by three to 10 percent.

As this tool is developed, I could see it being used to identify long-time missing children as they mature, said Ross Wolf, an associate professor of criminal justice at UCF.


comments powered by Disqus
Read more on:
 

PERMALINK

http://www.nerve.in/news:2535002382568
You can quote the permanent link above for a direct link to the story. We do not archive or expire our news stories.


STORY OPTIONS
  Email this story to a friend
  XML feed for Americas


 
COPYRIGHTS INFORMATION
All rights reserved for news content. Reproduction, storage or redistribution of Nerve content and articles in any medium is strictly prohibited.
Contact Nerve Staff for any feedback, corrections and omissions in news stories.
 

All rights reserved for the news content. Reproduction, storage or redistribution of Nerve content and articles in any medium is strictly prohibited.