June 20, 2014

New Facial Recognition Software Answers Whether Children Resemble Their Parents

redOrbit Staff & Wire Reports – Your Universe Online

A project launched in part to determine if a machine could determine whether children more closely resembled their mothers or fathers could help law enforcement officials locate missing youngsters and reunite people with their biological parents, according to researchers from the University of Central Florida.

Graduate Student Afshin Dehghan and colleagues from the UCF Center for Research in Computer Vision have created a facial recognition tool that they claim is capable of quickly matching pictures of children and their parents, the university explained in a statement Thursday.

The project, which will be presented next week during the IEEE Computer Vision and Pattern Recognition conference in Columbus, Ohio, started with more than 10,000 online images of famous parents and their offspring, and has blossomed into a tool capable of matching relatives and potentially even identifying photos of missing kids as they grow older.

“We wanted to see whether a machine could answer questions, such as ‘Do children resemble their parents?’ ‘Do children resemble one parent more than another?’ and ‘What parts of the face are more genetically inspired?’” Dehghan explained. While these topics are commonly discussed by anthropologists, the UCF team is looking to inspire new technological advances that can objectively analyze and evaluate data without human bias.

Ross Wolf, the associate dean in the UCF’s college of health and public affairs, as well as an associate professor of criminal justice and a law enforcement officer for more than two decades, said that the tool could potentially be “used to identify long-time missing children as they mature.”

While law enforcement officials already use facial recognition software, those programs lack the ability to identify the same features and characteristics in photos over time. The newly developed program could be capable of doing so. Dehghan’s team is looking to expand their research by analyzing how age, ethnicity and other similar factors can impact the resemblance of facial features, the university noted.

The study authors explain that their work is the latest foray into the long-standing debate as to whether or not computers are capable of thinking. Using actress Catherine Zeta Jones and her children as an example, they set out to use the technology to identify lesser-known features that the relatives have in common.

While people could look for something prominent, such as a shared smile, in the Hollywood star and her offspring, the researchers were hoping to find shared traits not typically viewed as significant, such as the chin, parts of the forehead, and even the left eye. They developed an algorithm to focus on those features, converting photos into a checkerboard of small regions and pulling out small snapshots of various segments of the face.

“The computer compared all the photos feature by feature and sorted them by the most probable match,” the university said. “The team found that its program not only did a better job of matching features of parents and their kids than random chance, but it also outperformed existing software… by 3 to 10 percent.”

Furthermore, the research provides evidence that children resemble their parents, often in unseen ways. In 63 percent of the cases, sons were more likely to resemble their fathers more closely than their mothers, while 82 percent of daughters were more likely to resemble their mothers, the authors said.

“Machines can learn through time. When a computer goes through thousands of images it knows what it has seen and is able to tell you,” said Dehghan, who was advised on the project by Mubarak Shah, director of the UCF Center for Research in Computer Vision.

Shah explained that advancements in technology have grown to the point where computer scientists can re-evaluate and expand upon the research of traditional scientific disciplines. He added that the new facial recognition technology could also be useful for other purposes, including helping homeland security officials determine relationships between terror suspects.