CT image sequence analysis for object recognition-a rule based 3-D computer vision system

The authors present a rule-based, three-dimensional (3-D) vision system for locating and identifying wood defects using topological, geometric and statistical attributes. A number of different features can be derived from the 3-D input scenes. These features and evidence functions are used to compute confidence values for object membership in different defect classes. The use of different knowledge sources in a set of independent and concise rules is illustrated.<<ETX>>