Remembering Hari Srihari

By Tom Dinki

Sargur “Hari” Srihari was, in many ways, a visionary.

A pioneer in pattern recognition, he taught machines to read handwriting. The impact of his work is felt everywhere, from technology that understands the scribbled addresses on our mail to machines that can determine if a criminal forged a signature.

“Dr. Srihari was, quite simply, a towering figure in computer science,” said University at Buffalo President Satish K. Tripathi. “Always at the cutting edge of innovation, he transformed pattern recognition, machine learning and computational forensics with findings that brought global renown to UB and had a profound impact on society.”

A SUNY Distinguished Professor of Computer Science and Engineering, Srihari founded the Center of Excellence for Document Analysis and Recognition (CEDAR) in the early 1990s. The center did groundbreaking research for the United States Postal Service and received funding of more than $60 million over 25 years. The work led to handwritten digit recognition being recognized as the “fruit fly” of artificial intelligence and machine learning.

In 2002, he conducted the first computationally based research to establish the individuality of handwriting, with important implications for the criminal justice system.

This work led to the first automated system, known as CEDAR-FOX, for determining whether two handwritten samples came from the same or different writers. The system was eventually extended to compare fingerprints and footprints.

Srihari was invited to serve as the only computer scientist on a National Academy of Sciences’ committee that produced an influential 2009 report on strengthening forensic sciences in the U.S., which has had a major impact in courts worldwide.

His research advances, which have received seven U.S. patents, also paved the way for the handwriting-recognition technology that is used in modern systems ranging from tablets to scanners. His early research work on 3D imaging remains influential in fields such as 3D printing.

“His work was used everywhere,” said Kemper Lewis, dean of the School of Engineering and Applied Sciences. “People leveraged it to solve even more complex problems.”

Beyond his extensive research over 45 years at UB, Srihari remained dedicated to teaching, recalls his wife, Rohini Srihari, professor and associate chair of the Department of Computer Science and Engineering.

“I watched him spend hours working on new lecture slides,” Rohini Srihari says. “He loved creating these and it was sometimes difficult to get him away from his desk.”

She recalled that he had several opportunities to go elsewhere over the years but enjoyed his work and the company of his colleagues too much to leave.

“He often commented that his professional success may not have been achievable had he been distracted by career moves and chasing new personal opportunities,” Rohini Srihari said.

To further honor his dedication to students, the Sargur N. Srihari Graduate Fellowship in Computer Science and Engineering was created to support a student pursuing a doctorate in machine learning in the Department of Computer Science and Engineering.

“We would like to thank all the people who have donated to the endowment fund, including many of Hari’s former students and friends,” Rohini Srihari says. “We hope that students who receive this fellowship demonstrate Hari’s thirst for advancing science.”

To honor his vision and dedication, UB posthumously awarded Srihari the President’s Medal at the School of Engineering and Applies Sciences’ 2022 graduate commencement ceremony in May.

That same month, the university held a symposium on campus in his honor. The symposium focused on Hari's professional accomplishments and included a series of talks and a panel discussion from faculty colleagues, current and former students, and distinguished guests.

Earlier this year, 113Y Davis Hall was renamed the Sargur Srihari Conference Room. The space, which is shared by CEDAR and the Center for Unified Biometrics and Sensors (CUBS), will feature a plaque and other items that commemorate Srihari’s legacy.

“Think about what happens in conference rooms,” Lewis says. “These are where big problems are tackled and transformational solutions are envisioned.”

Rohini Srihari said she hopes “the real legacy of the room will be that students and faculty will be meeting there long into the future to discuss cutting-edge technologies, building on the work that he accomplished.”

Born in Bangalore, India, Srihari earned an undergraduate degree in electrical and communication engineering from the Indian Institute of Science in Bangalore in 1970. Immigrating to the U.S. later that year, he obtained a master’s degree (1972) and PhD (1976), both in computer and information science, from The Ohio State University. After receiving his PhD, Srihari joined the faculty at Wayne State University. He came to UB in 1978.

During his career, Srihari authored more than 350 research papers with 20,000 citations (h-index=64); edited five books; and served as principal adviser to 40 doctoral students.

He was the recipient of numerous honors, among them the International Association for Pattern Recognition (IAPR)/International Conference on Document Analysis and Recognition Outstanding Achievements Award in 2011 for his outstanding and continued contributions to research and education in handwriting recognition and document analysis, and services to the community; the Distinguished Alumnus of The Ohio State University College of Engineering in 1999; and the UB Excellence in Graduate Mentoring Award in 2018.

He held fellowships in the IAPR and the Institute of Electronics and Telecommunications Engineers, and was a life fellow of the Institute of Electrical and Electronics Engineers (IEEE).

In his later years, Srihari remained an active faculty member, continuing to teach and supervise graduate students. He also developed an extensive set of lecture slides for machine learning, which are widely used in courses around the world.

His final teaching efforts were focused on integrating the wealth of research being produced in deep learning from various books, papers and blogs. He served as a visiting professor and scientist at his alma mater, the Indian Institute of Science, during spring 2020, and later established a scholarship there. “His wisdom and kindness are dearly missed,” says Jinhui Xu, professor and chair of the Department of Computer Science and Engineering.