Associate Professor Jeremy Dawson has received funding to collect biometric data that will be used to develop algorithm-based software systems (WVU Photo/Paige Nesbit).
A West Virginia University engineer is improving the accuracy of biometric identification that could lead to advances in healthcare, law enforcement and national security by collecting biometric data that will identify people at long distance and in difficult conditions.
Story of Adrianne Uphold, Multimedia specialist
MORGANTOWN, West Virginia—
Jeremy Dawson, an associate professor in the Department of Computer Science and Electrical Engineering at Lane, is the recipient of a four-year subcontract consisting of a base period and two option periods worth $750,000 to collect biometric data that will be used to develop a software algorithm. based on systems capable of performing full-body biometric identification at distances of up to 300 meters or more.
“The facial and full-body images we collect will help improve human recognition performance, making biometric systems fairer for different age, gender and ethnic groups and enabling better recognition in difficult conditions” , Dawson said.
The large-scale biometric dataset that will be collected will consist of images and videos of a person’s face, gait, shape and body type. The data will be used to improve the accuracy of the algorithm’s ability to identify a person from low-quality images, such as those captured by security cameras or drones.
“The monitored data will be collected at a relatively close distance with high quality cameras; then we will go out into the field and collect images at a longer distance and more extreme angles while asking our participants to walk, interacting with their phone or other specific actions,” Dawson said. “Collecting enough data in situations that would make it harder to recognize people is our primary goal.”
This multi-year research effort of the Intelligence Advanced Research Projects Activity (IARPA) is called the Biometric Altitude and Distance Recognition and Identification (BRIAR) program. Dawson’s research group aims to provide the biometrics research community with whole-body imaging data from hundreds of participants to address the challenges of identifying people at extreme distances and angles. The data will be collected from people who volunteer to participate, which requires people to give full consent for their data to be collected and used in the research.
“Facial recognition performance is strongly impacted by distance, individual pose, lack of adequate resolution; all of these things weigh heavily on the ability of facial recognition systems to correctly identify people,” Dawson said. “The data we collect will enable the development of new facial recognition algorithms robust enough to handle the harsh conditions present in real-world operational scenarios.”
WVU is a contractor to Systems and Technology Research (STR) and will provide data to STR and IARPA. Then the data will become a resource for the general biometrics research community and researchers can request the dataset to use for their systems.
“The algorithms currently used for facial recognition are all based on artificial intelligence and machine learning,” Dawson said. “These types of systems need to be developed using a lot of data captured under a lot of different conditions to work really, really well. will eventually get scattered among all the performers funded by the BRIAR program.”
Undergraduate and graduate students at the Benjamin M. Statler College of Engineering and Mineral Resources will gain real-world experience through this research project by developing the systems and testing the procedures used to collect the data and creating new techniques for manipulating biometric data.
“Our graduate students will oversee the development of the systems. They will test the systems that will collect the data, and even pre-process the data to prepare it for delivery,” Dawson said. “Undergraduates will also have the opportunity to help with data collection by being our sensor operators. Once graduate students have developed many systems, undergraduate operators gain invaluable experience with new technologies. camera, system implementation and troubleshooting.”
Dawson said this research will lead to the creation of new algorithms, but it will also improve existing systems.
“This opens the door to developing new algorithms that can take advantage of the rich variety of data we collect,” Dawson said. “We’re not just collecting face, gait, or full body, but we’re collecting all of those things that will be merged into the recognition pipeline to enable better performance on all systems.”
This research is based on work supported in part by the Office of the Director of National Intelligence (ODNI) and IARPA, through [2022-21102100005]. The opinions and conclusions contained herein are those of the authors and should not be construed as necessarily representing the official policies, expressed or implied, of ODNI, IARPA, or the United States Government. The United States Government is permitted to reproduce and distribute reprints for government purposes notwithstanding any copyright notices.
Contact: Paige Nesbit
Statler College of Engineering and Mineral Resources
304.293.4135, Paige Nesbit
For more information on West Virginia University Benjamin M. Statler College of Engineering and Mineral Resources news and events, contact our marketing and communications office:
E-mail: [email protected]