It’s been said that every face tells a story. But can a face also predict a person’s build or risk for acquiring certain obesity-related diseases? According to Guodong Guo, an assistant professor of computer science and electrical engineering at West Virginia University, the answer is yes.

Guo and his team have developed an algorithm that can analyze a photo and predict a person’s body mass index. BMI is a simple index of weight-for-height that is commonly used to classify underweight, overweight and obesity in adults.

“The software assess seven weight-related components in a face image, including the ratios of cheekbone width to jaw width, face length to cheekbone width and the average distance between eyebrow and eye,” Guo said. “This type of non-invasive analysis can have broad applications for combating obesity. It can also lead to large scale surveillance of public health and monitoring the health conditions of young children in schools.”

Since it was first announced in 2013, Guo’s work has received accolades from many sectors, including academia and government agencies.

Thanks to a $200,000 grant from the National Science Foundation, Guo is now working to refine the technology to make it more robust. In doing so, he is utilizing more sources of information, such as the visual information from both human face and body.

“The goal is to develop a visual information extraction approach to characterize and assess important body parameters related to health conditions,” Guo said. “The study is based on an accurate shape information extraction from the face and body based on computer vision techniques.”

According to Guo, the research and development from this project could be transformative for assessing human body parameters non-intrusively and precisely with a variety of real applications.

-WVU-

mcd/11/12/14

CONTACT: Mary C. Dillon, Statler College of Engineering and Mineral Resources
304.293.4086, Mary.Dillon@mail.wvu.edu

Follow @WVUToday on Twitter.