Professor named fellow of American Statistical Association

A Florida State University researcher who works to improve the visual-recognition capabilities of computers has received one of the top honors in his field.

RAY_6713.jpg

Anuj Srivastava, a Distinguished Research Professor in FSU’s Department of Statistics, has been named a fellow of the American Statistical Association (ASA), the world’s largest community of statisticians from the fields of academia, business, government and scientific research. The 18,000-member association selects no more than one-third of 1 percent of its members for the rank of fellow each year; a total of 62 people received the honor this year.

“It is a great honor to be named a fellow of the ASA,” Srivastava said. “I am an interdisciplinary scientist, working in an area that is at the intersection of statistics, engineering and computer science. Despite tremendous practical importance, this non-traditional research often misses out on awards and recognitions in favor of more traditional, well-established topics.

“I am glad that my research has earned recognition not just from the ASA but from other societies representing computer science and electrical engineering,” he said. “I am very much in debt to my collaborators and students who have all supported this research endeavor by giving their best. This and other honors would not have been possible without a team effort.”

In 2016, Srivastava was named a fellow of the Institute of Electric and Electronic Engineers (IEEE), a professional association dedicated to the advancement of technology, and a fellow of the International Association for Pattern Recognition (IAPR), which focuses on research involving pattern recognition, computer vision and image processing. He spent the 2014-2015 academic year conducting research at France’s University of Lille 1 after being named a Fulbright Scholar.

Srivastava works on “computer vision,” an interdisciplinary field in which researchers develop computer algorithms for recognizing objects from their images. The images can originate from anywhere, from YouTube videos and Xbox Kinect data to MRI scans and X-ray crystallography.

“The main idea is to analyze objects in images using their shape as a property that is quantifiable and amenable to statistical techniques,” he said. “For instance, morphology of anatomical structures in the human brain has been useful in diagnosis and assessments of cognitive impairments. Another application is to explore the relationship between structure and functionality of biological objects such as proteins and chromosomes.

Recently, Srivastava and colleagues have worked to adapt gaming sensors, such as Kinect, to help evaluate actions and activities performed by human beings in front of the sensors.

“This framework can be useful, for example, in helping patients learn, correct and perform physiotherapeutic exercises, all without visiting a clinic,” he said. “The science of understanding complex human behavior and emotional state using data collected from remote cameras is very deep and fascinating. While the sensors are advancing at a rapid rate, the tools for analyzing such data lag far behind. Our goal of developing systems that recognize and guide human activities is a step in addressing that issue.”

RAY_6695 copy.jpg

Xufeng Niu, chairman of the Department of Statistics, praised Srivastava as “an established leader in the field of high-dimensional data analysis with applications in computer vision and image understanding.

“Anuj has an outstanding record of research and creativity, and, consequently, has developed an impressive national and international reputation for himself and his research group at FSU,” Niu said. “I am very proud of his achievements. Congratulations to him for the prestigious honor.”

Srivastava earned a Ph.D. in electrical engineering from Washington University in St. Louis in 1996. He joined the Department of Statistics at FSU as an assistant professor in 1997, became a full professor in 2007 and was named a Distinguished Research Professor in 2014. He has published more than 200 peer-reviewed papers and co-authored a textbook, “Functional and Shape Data Analysis.” In addition, Srivastava has guided more than 20 students towards their Ph.D.s at FSU. As a sign of the high quality of their research, five of these students have won FSU’s prestigious Graduate Student Research and Creativity awards.