Abstract
High-level vision systems use object, scene or domain specific knowledge to interpret images. Unfortunately, this knowledge has to be acquired for every domain. This makes it difficult to port systems from one domain to another, and therefore to compare them. Recently, the authors of the ADORE system have claimed that object recognition can be modeled as a Markov decision process, and that domain-specific control strategies can be inferred automatically from training data. In this paper we demonstrate the generality of this approach by porting ADORE to a new domain, where it controls an object recognition system that previously relied on a semantic network.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Nagao, M. and T. Matsuyama, A Structural Analysis of Complex Aerial Photographs. 1980, New York: Plenum Press.
Ohta, Y., A Region-oriented Image-analysis System by Computer, Ph.D. thesis, 1980, Kyoto University: Kyoto, Japan.
McKeown, D.M., W.A. Harvey, and J. McDermott, Rule-Based Interpretation of Aerial imagery. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1985. 7(5): p. 570–585.
Clement, V. and M. Thonnat, A Knowledge-Based Approach to Integration of Image Processing. Computer Vision, Graphics and Image Processing, 1993. 57(2): p. 166–184.
Draper, B.A., et al., The Schema System. International Journal of Computer Vision, 1989. 2(2): p. 209–250.
Andress, K.M. and A.C. Kak, Evidence Accumulation & Flow of Control in a Hierarchical Spatial Reasoning System. AI Magazine, 1988. 9(2): p. 75–94.
Freuder, E.C. A Computer System for Visual Recognition using Active Knowledge Sources. in International Joint Conference on Artificial Intelligence. 1977. Cambridge, MA.
Niemann, H., et al., Ernest: A Semantic Network System for Pattern Understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990. 12(9): p. 883–905.
Paulus, D., et al. Active Knowledge-Based Scene Analysis. in International Conference on Vision Systems. 1999. Las Palmas de Gran Canaria, Spain: Springer-Verlag. p. 180–199.
Rimey, R.D. and C.M. Brown, Control of Selective Perception using Bayes Nets and Decision Theory. International Journal of Computer Vision, 1994. 12: p. 173–207.
Mann, W.B. and T.O. Binford. SUCCESSOR: Interpretation Overview and Constraint System. in Image Understanding Workshop. 1996. Palm Springs, CA: Morgan Kaufman.
Hwang, V.S.-S., L.S. Davis, and T. Matsuyama, Hypothesis Integration in Image Understanding Systems. Computer Vision, Graphics and Image Processing, 1986. 36(2): p. 321–371.
Stilla, U., E. Michaelson, and K. Lütjen, Structural 3D-Analysis of Aerial Images with a Blackboard-based Production System, in Automatic Extraction of Man-made Objects from Aerial and Space Images, A. Gruen, O. Kuebler, and P. Agouris, Editors. 1995, Birkhäuser: Basel. p. 53–62.
Thonnat, M., S. Moisan, and M. Crubézy. Experience in Integrating Image Processing Programs. in International Conference on Vision Systems. 1999. Las Palmas de Gran Canaria, Spain: Springer. p. 200–215.
Crevier, D. and R. LePage, Knowledge-based Image Understanding Systems. Computer Vision and Image Understanding, 1997. 67(2): p. 161–185.
Kosslyn, S.M., Image and Brain: The Resolution of the Imagery Debate. 1994, Cambridge, MA: MIT Press. 516.
Draper, B.A. and A.R. Hanson, An Example of Learning in Knowledge Directed Vision, in Theory and Applications of Image Analysis, P. Johansen and S. Olsen, Editors. 1992, World Scientific: Singapore. p. 237–252.
Draper, B.A., A.R. Hanson, and E.M. Riseman, Knowledge-Directed Vision: Control, Learning and Integration. Proceedings of the IEEE, 1996. 84(11): p. 1625–1637.
Draper, B.A., J. Bins, and K. Baek, ADORE: Adaptive Object Recognition. Videre, 2000. 1(4): p. 86–99.
Peng, J. and B. Bhanu, Closed-Loop Object Recognition Using Reinforcement Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998. 20(2): p. 139–154.
Au, W. and B. Roberts. Adaptive Configuration and Control in an ATR System. in Image Understanding Workshop. 1996. Palm Springs, CA: Morgan Kaufman. p. 667–676
Maloof, M.A., et al. Learning to Detect Rooftops in Aerial Images. in Image Understanding Workshop. 1997. New Orleans: Morgan Kaufman. p. 835–846
Draper, B.A., Learning Control Strategies for Object Recognition, in Symbolic Visual Learning, K. Ikeuchi and M. Veloso, Editors. 1997, Oxford University Press: New York. p. 49–76.
Ahlrichs, U., D. Paulus, and H. Neiman. Integrating Aspects of Active Vision into a Knowledge-Based System. in International Conference on Pattern Recognition. 2000. Barcelona.
Draper, B.A. and K. Baek. Unsupervised Learning of Biologically Plausible Object Recognition Strategies,. in IEEE International Workshop on Biologically Motivated Computer Vision. 2000. Seoul: IEEE CS Press.
Priese, L. and V. Rehrmann. On Hierarchical Color Segmentation and Applications. in IEEE Conference on Computer Vision and Pattern Recognition. 1993.
Paulus, D. and J. Hornegger, Pattern Recognition of Images and Speech in C++, in Advanced Studies in Computer Science. 1997, Vieweg: Braunschweig.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Draper, B.A., Ahlrichs, U., Paulus, D. (2001). Adapting Object Recognition across Domains: A Demonstration. In: Schiele, B., Sagerer, G. (eds) Computer Vision Systems. ICVS 2001. Lecture Notes in Computer Science, vol 2095. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48222-9_17
Download citation
DOI: https://doi.org/10.1007/3-540-48222-9_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42285-3
Online ISBN: 978-3-540-48222-2
eBook Packages: Springer Book Archive