Abstract
An intelligent method in the field of object recognition should be able to work in the real world, i.e. the objects could be complex and deformed. Such a method consists of two main parts: Generating automatically the characteristics of object classes from known samples of objects and classifying unknown objects with the help of the learnt characteristics. The presented method is based on our work introduced in (2000) where important contour sections are detected in order to distinguish between contours.
Our further developments contain (un) supervised learning of a knowledge base consisting of Significant Contour Sections of complex, deformed and discrete contours and a hierarchical classification method for unknown contours based on this knowledge base. The classifier does not need feature vectors of an equal number of elements.
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
Basri, R., Costa, L., Geiger, D., and Jacobs, D. (1998): Determining the Similarity of Deformable Shapes. Vision Research, 38, 2365–2385.
Latecki, L. and Lakämper, R. (1999): Convexity Rule for Shape Decomposition Based on Discrete Contour Evolution. Computer Vision and Image Understanding (CVIU), 73(3), 441–454.
Loncaric, S. (1998): A Survey of Shape Analysis Techniques. Pattern Recognition, Vol. 31, No. 8, 983–10
Pechtel, D. and Kuhnert, K.-D. (1999): Automatic Generation of Significant and Local Feature Groups of Complex and Deformed Objects, Proc. of ICIAP’99, Venice, Italy, 340–345.
Pechtel, D. and Kuhnert, K.-D. (2000): Generating Automatically Local Feature Groups of Complex and Deformed Objects. In: Gaul, W. and Decker, R. (eds.): Classification and Information Processing at the Turn of the Millenium. Springer, Heidelberg, 237–244.
Sankoff, D. and Kruskal, B. (Eds.) (1983): Time Warps, String Edits, and Macromolecules. Addison-Wesley, Reading, Massachusetts.
Siddiqi, K. and Kimia, B.B. (1995): Parts of Visual Form: Computational Aspects. IEEE Transactions PAMI, 17, 239–251.
Ullman, S. (1996): High-level Vision. A Bradford Book, MIT Press, Cambridge, Massachusetts
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pechtel, D., Kuhnert, KD. (2002). Towards Feature Fusion — A Classifier on the Basis of Automatically Generated Significant Contour Sections. In: Gaul, W., Ritter, G. (eds) Classification, Automation, and New Media. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-55991-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-55991-4_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43233-3
Online ISBN: 978-3-642-55991-4
eBook Packages: Springer Book Archive