A Constraint Satisfaction Framework with Bayesian Inference for Model-Based Object Recognition
A general (application independent) framework for the recognition of partially hidden 3-D objects in images is presented. It views the model-to-image matching as a constraint satisfaction problem (CSP) supported by Bayesian net-based evaluation of partial variable assignments. A modified incremental search for CSP is designed that allows partial solutions and calls for stochastic inference in order to provide judgments of partial states. Hence the detection of partial occlusion of objects is handled consistently with Bayesian inference over evidence and hidden variables. A particular problem of passing different objects to a machine by a human hand is solved while applying the general framework. The conducted experiments deal with the recognition of three objects: a simple cube, a Rubik cube and a tea cup.
Unable to display preview. Download preview PDF.
- 2.Faugeras, O.: Three-dimensional computer vision. A geometric viewpoint. The MIT Press, Cambridge (1993)Google Scholar
- 4.Niemann, H., Sagerer, G., Schroder, S., Kummert, F.: ERNEST: A semantic network system for pattern understanding. IEEE Trans. PAMI 12, 883–905 (1990)Google Scholar
- 6.Russel, S., Norvig, P.: Artificial Intelligence. A modern approach, 2nd edn. Prentice Hall, Englewood Cliffs (2002)Google Scholar
- 7.Chan, K., Cheung, Y.: Fuzzy-attribute graph with application to chinese character recognition. IEEE Trans. SMC 22, 402–410 (1992)Google Scholar
- 9.Duda, R.O., Hart, P.E., Stork, D.: Pattern Classification and Scene Analysis, 2nd edn. J. Wiley, New York (2001)Google Scholar
- 10.Kasprzak, W., Szynkiewicz, W., Czajka, L.: Rubik’s Cube Reconstruction from Single View for Service Robots. Machine Graphics & Vision 15(2/3), 451–460 (2006)Google Scholar