Abstract
We report on a case study showing on recognition of objects under perspective distortion in projected 2d images. We use symbolic descriptions and yield similar results as heuristic or statistical methods. The knowledge is modeled in so-called TGraphs which are typed, attributed, and ordered directed graphs. We combine the search in the state space with a maximum weight bipartite graph-matching and in consequence we reduce the numerous amount of hypotheses. Furthermore we use hash tables to increase the runtime efficiency. As a result we reduce the runtime up to a factor of five in comparison to the system without hash tables and achieve a detection rate of 90.6% for a data set containing 968 perspective images of poker cards and domino tiles. Therefore, we show that model-based object recognition using symbolic descriptions is on a competitive basis.
Similar content being viewed by others
References
C. Beierle and G. Kern-Isberner, Methoden wissensbasierter Systeme-Grundlagen, Algorithmen, Anwendungen, Vieweg, 1. Auflage (2006).
M. Bollmann, R. Hoischen, M. Jesikiewicz, C. Justkowski, and B. Mertsching, “Playing Domino: A Case Study for an Active Vision System,” in Computer Vision Systems, Ed. by H. Christensen (1999), p. 392 ff.
D. Cremers, N. Sochen, and C. Schnörr, “A Multiphase Dynamic Labeling Model for Variational Recognition-Driven Image Segmentation,” Int. J. Comput. Vision 66(1), 67–81 (2006).
D. Crevier and R. Lepage, “Knowledge-Based Image Understanding Systems: A Survey,” Comp. Vision Image Understand. 67(2), 161–185 (1997).
J. Ebert, “Metamodels Taken Seriously: The Tgraph Approach,” in Proc. 12th European Conf. on Software Maintenance and Reengineering, Ed. by K. Kontogiannis, C. Tjortjis, and A. Winter (Piscataway, NJ, 2008).
J. Ebert, V. Riediger, and A. Winter, “Graph Technology in Reverse Engineering, the Tgraph Approach,” in Proc. 10th Workshop Software Reengineering (WSR 2008), Ed. by R. Gimnich, U. Kaiser, J. Quante, and A. Winter (Bonn, 2008), Vol. 126, pp. 67–81.
K. Falkowski, “A Component Concept for Scientific Experiments-Focused on Versatile Visual Component Assembling,” in Proc. 15th Int. Workshop on Component-Oriented Programming (WCOP) (Prague, 2010), pp. 31–38.
K. Falkowski and J. Ebert, “Graph-Based Urban Object Model Processing,” in Proc. Object Extraction for 3D City Models, Road Databases, and Traffic Monitoring-Concepts, Algorithms, and Evaluation (CMRT) 2009, Ed. by U. Stilla, F. Rottensteiner, and N. Paparoditis, (Paris, 2009), Vol. 38–3/W4, pp. 115–120.
K. Falkowski and J. Ebert, “The Stor Component System,” Tech. Rep. 14/2009 (Institut für Softwaretechnik, Universität Koblenz-Landau, 2009).
R. I. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, 2nd ed. (Cambridge Univ. Press, 2003).
J. Hois, “Modularizing Spatial Ontologies for Assisted Living Systems,” Knowledge Sci., Eng.Manag., pp. 424–435 (2010).
J. Hois, “Towards Combining Ontologies and Uncertain Knowledge,” in Proc. 3rd Workshop on Combining Probability and Logic (University of Kent, Canterbury, 2007).
L. Hotz and B. Neumann, “High-Level Expectations for Low-Level Image Processing,” in Proc. KI 2008: Advances in Artificial Intelligence (Kaiserslautern, 2008), pp 87–94.
M. K. Hu, “Visual Pattern Recognition by Moment Invariants,” IEEE Trans. Inf. Theory 8(2), 179–187 (1962).
H. W. Kuhn, “The Hungarian Method for the Assignment Problem,” Naval Res. Logist. Quarterly 2, 83–97 (1955).
F. Kummert, G. Sagerer, and H. Niemann, A Problemindependent Control Algorithm for Image Understanding (Universität Bielefeld, 1992), pp. 297–301.
E. Michaelsen, M. Arens, and L. Doktorski, “Interaction of Control and Knowledge in a Structural Recognition System,” in Proc. 32nd Annu. German Conf. on Advances in Artificial Intelligence (Springer-Verlag, 2009), pp. 73–80.
B. Neumann, “Bayesian Compositional Hierarchiesa Probabilistic Structure for Scene Interpretation,” Tech. Rep. FBI-HH-B-282/08 (Department of Informatics, Hamburg Univ., 2008).
H. Niemann, G. Sagerer, S. Schröber, and F. K. Ernest, “A Semantic Network System for Pattern Understanding,” IEEE Trans. Pattern Anal. Mach. Intell. 9, 883–905 (1990).
H. Niemann, Pattern Analysis and Understanding (Springer Verlag, Heidelberg, 1990), Vol. 4.
F. Quint, “Aerial Image Understanding Using Digital Map Based Semantic Models,” in Proc. Euroconference GIS, Union Europeenne, Project Capital Humain et Mobilite, ENSG (Saint-Mande, France, 1995).
F. Quint, “Kartengestützte Interpretation monokularer Luftbilder,” PhD Thesis (Univ. Fridericiana zu Karlsruhe (TH), Karlsruhe, 1997).
T. Reineking, N. Schult, and J. Hois, “Evidential Combination of Ontological and Statistical Information for Active Scene Classification,” in Proc. Conf. on Knowledge Engineering and Ontology Development (KEOD’09) (Madeira, 2009).
G. Sagerer, Darstellung und Nutzung von Expertenwissen für ein Bildanalysesystem (Springer, Berlin, 1985).
J. Schmittwilken, D. Dörschlag, and L. Plümer, “Attribute Grammar for 3D City Models,” in Urban and Regional Data Management: UDMS Annual 2009: Proc. Urban Data Management Soc. Symp. 2009 (Ljubljana, June 24–26, 2009), p. 49.
E. Seemann, B. Leibe, and B. Schiele, “Multiaspect Detection of Articulated Objects,” in Proc. Conf. on Computer Vision and Pattern Recognition (CVPR’06) (New York, 2006), Vol. 2, pp. 1582–1588.
G. Shafer, A Mathematical Theory of Evidence (Princeton Univ. Press, Princeton, 1976).
S. Theodoridis and K. Koutroumbas, Pattern Recognition, 4th ed. (Acad. Press, 2009).
S. Wirtz, M. Häselich, and D. Paulus, “Model-Based Recognition of Domino Tiles Using Tgraphs,” in Pattern Recognition, Proc. 32nd DAGM (Darmstadt, 2010), pp. 101–110.
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Stefan Wirtz obtained a diploma in Biomathematics (Dipl.-Math. (FH)) from the University of applied science RheinAhrCampus Remagen in 2008. Hi is now working for the Institute of Computational Visualistics in the Working Group Active Vision (Prof. Paulus) at the University of Koblenz-Landau since 2009. There he works as PhD student in the project “Software Techniques for Object Recognition (STOR)” which is funded by the German Research Foundation (DFG). His scientific interests can be associated with the fields of Image Processing, Pattern Recognition and especial the handling of uncertain knowledge.
Kerstin Falkowski obtained a diploma in Computational Visualistics (Dipl.-Inform.) from the University of Koblenz-Landau, Koblenz, Germany in 2005. Since then she is working at this university as PhD student for the Institute of Software Technology in the Working Group of Prof. Ebert. There she works in the project “Software Techniques for Object Recognition (STOR)” which is funded by the German Research Foundation (DFG). Her scientific interests are graph-based knowledge processing and component concepts.
Dietrich Paulus obtained a Bachelor degree in Computer Science from University of Western Ontario, London, Canada, followed by a diploma (Dipl.-Inf.) in Computer Science and a PhD (Dr.-Ing.) from Friedrich-Alexander University Erlangen-Nuremberg, Germany. He obtained his habilitation in Erlangen in 2001. Since 2001 he is at the institute for computational visualistics at the University Koblenz-Landau, Germany where he became a full professor in 2002. He is head of the Active Vision Group (AGAS). His primary interests are computer vision and robot vision.
Rights and permissions
About this article
Cite this article
Wirtz, S., Paulus, D. & Falkowski, K. Model-based recognition of 2D objects under perspective distortion. Pattern Recognit. Image Anal. 22, 419–432 (2012). https://doi.org/10.1134/S105466181202023X
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S105466181202023X