Practicing vision: Integration, evaluation and applications

Computer vision has emerged as a challenging and important area of research, both as an engineering and a scientiic discipline. The growing importance of computer vision is evident from the fact that it was identiied as one of the \Grand Challenges" and also from its prominent role in the National Information Infrastructure. While the design of a general-purpose vision system continues to be elusive, machine vision systems are being used successfully in speciic application domains. Building a practical vision system requires a careful selection of appropriate sensors, extraction and integration of information from available cues in the sensed data, and evaluation of system robustness and performance. We discuss and demonstrate advantages of (i) multi-sensor fusion, (ii) combination of features and classi-ers, (iii) integration of visual modules, and (iv) admissibility and goal-directed evaluation of vision algorithms. The requirements of several prominent real world applications such as biometry, document image analysis, image and video database retrieval, and automatic object model construction ooer exciting problems and new opportunities to design and evaluate vision algorithms.