Mobile Interactive Support System for Time-Critical Document Exploitation

Computer Assisted Visual Interactive Recognition, or CAVIAR, has proven to be an effective methodology for integrating human and machine expertise in addressing challenging pattern recognition tasks. In this paper, we examine the application of the CAVIAR paradigm to problems arising in real-time document analysis in the field. We identify hurdles we expect to encounter, propose potential solutions, and describe an evaluation framework to help determine whether this is a fruitful line of research.