Sargur “Hari” Srihari, an internationally renowned professor of computer science at UB who taught computers to read handwriting and significantly advanced the fields of pattern recognition, computer forensics, and machine learning, died March 8 from glioblastoma. He was 72 years old.
SUNY Professor Emeritus of Computer Science and Engineering and a UB faculty member for more than 40 years, Srihari has established the university as a leading center for pattern recognition and machine learning. He founded the Center of Excellence for Document Analysis and Recognition (CEDAR), which performed groundbreaking research for the U.S. Postal Service in the 1990s, eventually teaching machines to read handwritten envelopes. This work at CEDAR, which received total funding of more than $60 million over 25 years, led to the recognition of handwritten digits as the “fruit fly” of artificial intelligence and machine learning.
“Dr. Srihari was, quite simply, a towering figure in computing,” said President Satish K. Tripathi. “Always at the forefront of innovation, he transformed pattern recognition, machine learning, and computer forensics with discoveries that brought worldwide fame to UB and had a profound impact on society.
“Beyond his truly outstanding research contributions, Hari was a dedicated academic citizen and devoted mentor. In his own patient, gentle and encouraging way, he inspired generations of budding computer scientists to excel in their own right,” Tripathi said.
“As we at UB join the global computing community in mourning the passing of this incomparable scholar, I would like to extend my deepest condolences to Hari’s wife, Professor Rohini Srihari, his children and his whole family.”
Srihari’s research advances, which were awarded seven US patents, paved the way for handwriting recognition technology used in modern systems ranging from tablets to scanners. His early research in 3D imaging also remains influential in areas such as 3D printing.
Srihari would later become a pioneer in the field of computer forensics. In 2002, he conducted the first computational research to establish the individuality of handwriting, with important implications for the criminal justice community.
This work led to the first automated system, known as CEDAR-FOX, to determine whether two manuscript samples were from the same writer or from different writers. The writing work was eventually extended to comparing fingerprints and shoe prints. This work led to Srihari being invited to become the only computer scientist on a committee of the National Academy of Sciences who produced an influential 2009 report on strengthening forensic science in the United States that had an impact major in courts around the world.
“It’s a huge loss, not only for UB’s computer science and engineering family, but for the computer science world,” said Jinhui Xu, professor and director of the Department of Computer Science and Engineering. engineering. “Hari was greatly admired by his students, UB faculty members, and scholars around the world.”
Kemper Lewis, Dean of the School of Engineering and Applied Science, called Srihari a “renowned artificial intelligence researcher” who was a “widely respected expert in statistical pattern recognition and deep learning.”
“Hari cherished his role as a researcher, professor and scientist, and he will be deeply missed by his department, our school and our university,” Lewis said.
Srihari is survived by his wife of 45 years, Rohini, a professor of computer science and engineering at UB; his sons, Dileep Srihari and Ashok Srihari (Caroline); and her granddaughter, Vera Srihari.
A memorial fund, the Professor Sargur (Hari) Srihari Memorial Fund, has been established to support scholarships. Donations can be made here.
Born in Bangalore, India, Srihari graduated with an undergraduate degree in Electrical and Communications Engineering from the world renowned Indian Institute of Science in Bangalore in 1970. Immigrating to the United States later that year, he earned a master’s degree (1972) and doctorate (1976), both in computer science and information science, from The Ohio State University. His doctoral thesis focused on the design and evaluation of classification algorithms for a type of pattern recognition related to the radar identification of aircraft.
After earning his doctorate, Srihari joined the faculty at Wayne State University. He came to UB in 1978.
During his career, Srihari has authored over 350 research papers with 20,000 citations (h-index=64); edited five books; and served as senior advisor to 40 PhD students.
He has received numerous accolades, including the IAPR/ICDAR Outstanding Achievement Award in 2011 for outstanding and continuing contributions to research and education in handwriting recognition and document analysis, and community services; alumnus emeritus of the Ohio State University College of Engineering in 1999; and the UB Excellence in Graduate Mentoring Award in 2018.
He was a Fellow of the International Association for Pattern Recognition (IAPR) and the Institute of Electronics and Telecommunications Engineers (IETE, India), and was a Life Member of the Institute of Electrical and Electronics Engineers (IEEE).
In his later years, Srihari remained an active faculty member, continues to teach and supervise graduate students. He has also developed a comprehensive set of course slides for machine learning, which are widely used in courses around the world.
His latest teaching efforts have focused on integrating the wealth of research produced into deep learning from various books, articles and blogs. He was a visiting professor and scientist at his alma mater, the Indian Institute of Science, in the spring of 2020 and later established a fellowship there. During the pandemic, he started recording videos of his explanation of deep learning topics, and also broadcast live.
He enjoyed traveling with Rohini to Washington, DC and Florida to visit their sons and granddaughter. He also continued to read avidly while pursuing his lifelong love of history, science, and gardening.