Abstract
We present a model-based method for object identification in images from natural scenes. It has successfully been implemented for the classification of cars based on their rear view. In a first step characteristic features such as lines and corners are detected within the image. Generic models of object-classes, described by the same set of features, are stored in a database. Each model represents a whole class of objects (e.g. passenger cars, vans, big trucks). A pre-processing module suggests a region of interest. A method based on the elastic net technique [2] then is used to map the model on the image features. During this iterative process the model is allowed to undergo changes in scale, position and certain deformations. Deformations are kept within limits such that one model can fit to all objects belonging to the same class, but not to objects of other classes. In each iteration step a value to assess the matching process is obtained.
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.
Similar content being viewed by others
References
Durbin, R., Szeliski, It. and Yuille, A., An Analysis of the Elastic Net Approach to the Traveling Salesman Problem, Neural Computation, Vol. 1, pp. 348–358, 1989.
Durbin, R. and Willshaw, D., An analogue approach to the traveling salesman problem using an elastic net method, Nature, Vol. 326, No. 6114, pp. 689–691, 1987.
Nevatia, R. and Babu, K. R., Linear Feature Extraction and Description, Computer Graphics and Image Processing, Vol. 13, pp. 257–269, 1980.
Ullman, S., Aligning pictorial descriptions: An approach to object recognition, Cognition, Vol. 32, pp. 193–254, 1989.
Zielke, T., Brauckmann, M. and von Seelen, W., Intensity and Edge-Based Symmetry Detection Applied to Car-Following, Proceedings of ECCV-92 (Lecture Notes in Computer Science 588), G. Sandini (Editor), Springer-Verlag, Berlin, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schwarzinger, M., Noll, D., v. Seelen, W. (1992). Object recognition with deformable models using constrained elastic nets. In: Fuchs, S., Hoffmann, R. (eds) Mustererkennung 1992. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-77785-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-77785-1_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55936-8
Online ISBN: 978-3-642-77785-1
eBook Packages: Springer Book Archive