SUNY Distinguished Professor Venu Govindaraju is the Interim Vice President for Research & Economic Development at the University at Buffalo, the State University of New York (UB). He is responsible for managing UB's research enterprise, university/industry relations and economic development. The university's research contributes to the economic and cultural vitality of New York State and around the world, by discovering knowledge that helps resolve global challenges.
Govindaraju also is the founding director of the Center for Unified Biometrics and Sensors (CUBS). He holds four patents, has received several major professional society awards and co-authored about 400 scientific papers. He serves on the editorial boards of premier journals and belongs to a select group of computer scientists who are fellows of both the Association for Computing Machinery and the Institute of Electrical and Electronic Engineers.
PhD, University at Buffalo, State University of New York, 1992
MS, University at Buffalo, State University of New York, 1988
BTech, Indian Institute of Technology (IIT), Kharagpur, 1986
Govindaraju's research focuses on machine learning and pattern recognition and his seminal work in handwriting recognition was at the core of the first handwritten address interpretation system used by the U.S. Postal Service. He has been the principal investigator or co-principal investigator on roughly $65 million in research funding.
Major Professional Society Awards
Conference Best Paper/Competition Awards
Industry Faculty Research Awards
University at Buffalo Awards
Document Recognition and Retrieval
Handwriting Recognition Models: Developed the first handwritten word recognition module suitable for real time applications using an innovative dynamic matching algorithm to assign automatically segmented pieces of words to lexical entities.
Pattern Recognition Techniques: Developed the first taxonomy of the complexity of classification combination methodologies and a guideline for choosing a particular type of fusion technique.
Document Analysis Systems: His innovative methodology enabled solutions to several practical document processing systems. The postal handwritten address system was deployed in the field with unprecedented success; bank check reading systems could leverage the recognition of the legal amounts written in long hand; and new paradigms for recognition of medical forms became possible by modeling the relationships between handwriting and medical topics.
Innovative Applications: Developed the first simulation of human-like handwriting for designing CAPTCHAs to exploit the differential in handwriting reading proficiency between humans and machines. Innovated methods that stochastically model imperfect word segmentation inherent in handwriting which, along with his highly original work on transcript mapping, is bound to significantly impact the search engines of the future.
Fingerprint Templates and Matching: Explored innovative enhancement and binarization techniques for fingerprint images and was first to formulate the matching algorithm as a minimum cost-flow problem and coupled breadth-first search algorithm. Govindaraju proposed a novel indexing method based on minutia k-plet paths whose search time remains constant even when increasing the number of enrolled persons.
Face and Facial Expression Analysis: Proposed one of the earliest model based face recognition method and developed a face matching system based on semantic descriptors. Verified the individuality of facial expressions and showed that either displacements of facial features or the frequencies of particular expressions could be used as biometric modalities. His innovative methods for automated detection of deceit in facial expressions used changes in facial geometry, texture and changes in the eye movements.
Smart Environments: Formulated a probabilistic framework for person identification and tracking in smart environments and introduced novel methods for confirming the identity of online users.
The Center for Unified Biometrics and Sensors (CUBS) was established in October 2003 with the mission of advancing the science of biometric technologies for both civilian and homeland security applications by integrating pattern recognition and machine learning algorithms with sensors technology. Govindaraju is its founding director.
CUBS research and development activities in machine learning span two strategic application areas, biometrics and language technologies. The activities range from research on Department of Defense projects and developing prototype devices for the industry, to organizing major technical conferences and training graduate students. Federal sponsors include the Army Research Labs, the Central Intelligence Agency, the Defense Intelligence Agency, and the National Science Foundation. Industry sponsors include BBN Raytheon, Google, HP, IBM, and Lockheed Martin.
Govindaraju has contributed significantly to the advancement of his fields by mentoring post-doctoral fellows and supervising dozens of graduate students. Upon graduation, the fellows and students have been employed globally in industry-leading companies and prestigious universities.
Govindaraju has been the primary advisor for 31 doctoral students and 15 masters students. Their research has ranged from handwriting analysis and recognition to cybersecurity to statistical modeling for medical image segmentation. His students have worked on fingerprint detection, transfer learning for probability density estimation and language motivated approaches for human action recognition and spotting. His post-doctoral fellows have focused on Arabic handwriting recognition and fusion of classifiers in biometric systems.
516 Capen Hall
University at Buffalo, NY 14260-1611
Innovative biometric technologies from the Center for Unified Biometrics and Sensors (CUBS) helps homeland security.