Computer Vision and Machine Learning

The Computer Vision and Machine Learning focus area builds on the pioneering work at UB in enabling AI innovation in language and vision analytic sub-systems and their application to the fields of document analysis, biometrics, and scene understanding.

The goal of current projects in this thrust area is to achieve a holistic understanding of the visual scene to realize (personalized) smart spaces for societal benefit – making sense of multilingual text, objects, and people (in the wild) that typically populate a visual scene.

Current Research Projects

Biometrics

  • Modalities: Face, Fingerprint, Iris, Handwriting, Keystroke dynamics, Cognitive biometrics
  • Emotion/micro-expression classification, deceit detection, behavioral analysis

Document Analysis and Recognition

  • Multilingual handwriting recognition (Indic, Arabic, Asian, Roman scripts)
  • Historical documents processing (Ancient manuscripts, Palm leaves)
  • Automated forms processing (Healthcare, Postal)  
  • Lecture video summarization

The Computer Vision and Machine Learning research area is led by Srirangaraj (Ranga) Setlur. Mr. Setlur is a Principal Research Scientist at UB’s Center for Unified Biometrics and Sensors (CUBS). The Center’s mission is the advancement of biometric technologies for both civilian and homeland security applications via pattern recognition, machine learning algorithms and sensors technology. (CUBS) has been funded in the past by the Army Research Labs, the CIA, Google, IBM, and Lockheed Martin to name but a few. 

Affiliated Faculty

Affiliated Organizations