| Object recognition has been a central task to the computer vision community since the early days of using computers to identify hand-written characters. Through these fruitful decades of increasing machine intelligence, we have taken huge strides in solving specific tasks, such as classification systems for automated assembly line inspection, hand-written character recognition in mail sorting machines, bill counting and inspection in automated teller machines, to name a few. Despite these successful applications, computers have made little progress in generalizing object appearance, even under moderately controlled sensing environments. On the other hand, humans can effortlessly categorize hundreds of objects present in highly complex scenarios. We believe this success in pattern recognition is due to the variety of cues utilized by the human vision system. Therefore, the central topic is this thesis is a cue-based approach to object categorization. (Abstract shortened by UMI.). |
