Using uncertainty techniques to aid defect classification in an automated visual inspection system

This research investigates how Artificial Intelligence techniques can be applied to an Automated Visual Inspection (AVI) system to enable the construction of a defect classification scheme. Whilst there are many defect detection systems on the market, there are few commercial products which also provide satisfactory classification. It is suggested there are two reasons why classification techniques are difficult to apply. First, most problems assume that a description of what is to be classified already exists. In many applications this is not the case. Second, the working environment of many 'real world' applications is continually open to change. The knowledge acquisition task is not a one off process since the data which describes the objects to be classified will vary over time. This research analyses how Uncertainty Management Techniques (UMT) can be applied to improve the classification process.