a composite image depicting a human eye, fingerprint, and biometric measurements.

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.

  • 4/20/20
    Professor Govindaraju's work in handwriting recognition was at the core of the first handwritten address interpretation system used by the United States Postal Service.
  • 11/6/19
    CUBS projects are funded by industry and government agencies. 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.
  • 12/8/20
    The Center for Unified Biometrics and Sensors (CUBS), at the University at Buffalo is releasing a new handwriting dataset to the research community. The IBM_UB dataset is a bi-modal (online and offline), multilingual corpus of ground-truthed handwritten documents. It contains a variety of handwritten content ranging from pages of free form cursive writing, to forms, spontaneously written letters, and tables of words, isolated characters and symbols. We expect this dataset to be a valuable resource for multilingual OCR development and for IR applications.
  • 11/20/19
    Scholarly activities at CUBS include the completion of 39 PhD dissertations, 17 MS theses, 7 patents, 17 books/edited volumes, and over 400 journal, conference, and workshop papers. CUBS alumni are employed at BBN Technologies, Fujitsu Labs, eBay, Google, Siemens Medical Solutions, and Yahoo Research.