PRACTICING VISION - INTEGRATION, EVALUATION AND APPLICATIONS

Computer vision has emerged as a challenging and important area of res earch, both as an engineering and a scientific discipline. The growing importance of computer vision is evident from the fact that it was id entified as one of the ''Grand Challenges'' and also from its prominen t role in the National Information Infrastructure. While the design of a general purpose vision system continues to be elusive, machine visi on systems are being used successfully in specific application domains . Building a practical vision system requires a careful selection of a ppropriate sensors, extraction and integration of information from ava ilable cues in the sensed data, and evaluation of system robustness an d performance. We discuss and demonstrate advantages of (i) multi-sens or fusion, (ii) combination of features and classifiers, (iii) integra tion of visual modules, and (iv) admissibility and goal-directed evalu ation of vision algorithms. The requirements of several prominent real world applications such as biometry, document image analysis, image a nd video database retrieval, and automatic object model construction o ffer exciting problems and new opportunities to design and evaluate vi sion algorithms. Copyright (C) 1997 Pattern Recognition Society.