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.

  • Pioneers in AI Systems
    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.
  • Projects
    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.
  • Datasets
    Fingerprint spoof attacks represent one of the most prevalent forms of biometric presentation attacks. While significant progress has been made in framing fingerprint spoof detection as a general image classification problem, limited attention has been given to treating it as a temporal learning problem. The distinctions in the elastic properties between authentic and synthetically created counterfeit fingerprints can be more accurately captured under motion-induced gestures during acquisition. In this study, we introduce a novel method for detecting fake fingerprints by deliberately introducing distortions through sliding and twisting motions during acquisition.
  • Research Highlights
    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.