Using Graphical Models to Unobtrusively Assess Student Performance in Educational Image Processing Activities

Unobtrusive educational assessment is a means of measuring student progress using the byproducts of authentic learning activities. It is difficult to perform well. Using a new technology based on graphical models, unobtrusive assessment can become more practical. We describe how we apply our techniques in teaching image processing to undergraduates. Our methods for unobtrusive assessment are applicable when learning activities are computer-based and involve the manipulation of tools such as construction kits, simulations, and programming languages.