Abstract
Image segmentation is an important part in any computer vision framework. However, the transition from local low-level representations to useful structures and relations in the intermediate levels has turned out to be a truly difficult problem. This paper addresses the difficult transition from low-level into intermediate-level vision, where the latter deals with producing a description of image and scene attributes in which more global relations are made explicit. We propose to combine a rich attributed contour representation with very general geometric contour relations. The implemented geometric relations, which are proximity, curvilinearity, parallelism and corner-like relations, allow to handle general man-made objects whose projected surfaces can be described by combinations of the defined relations. The combination of rich image attributes and geometric relations allows to discriminate between strong and weak contour relations. Strong relations require that not only the geometrical constraints are met but also that the contour attributes (e.g. photometric) are in agreement. We describe the approach and show some preliminary results.
The research described in this paper has been supported by the Swiss National Science Foundation, Grant no. 20–36431.92.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Dubuc B. and S.W. Zucker (1994). Curve-like Sets, Normal Complexity, and Representation. In International Conference on Pattern Recognition, pp. 216–221.
Freeman W.T. (1992). Steerabie Filters and Local Analysis of Image Structure. PhD thesis, MIT, Media Laboratory, Cambridge MA.
Fua P. and A.J. Hanson (1988). Extracting Generic Shapes Using Model-Driven Optimization. In DARPA Image Understanding Workshop, pp. 994–1004, Cambridge, Massachusetts.
Grimson W.E.L (1990). Object Recognition by Computer: The Role of Geometric Constraints. The MIT Press, Cambridge, Massachusetts.
Havaldar P., G. Medioni, and F. Stein (1994). Extraction of Groups for Recognition. In J.O. Eklundh, editor, Computer Vision — ECCV’94, volume I, pp. 251–261. Springer Verlag, Berlin.
Heitger F., L. Rosenthaler, R. von der Heydt, E. Peterhans, and O. Kubier (1992). Simulation of neural contour mechanisms: From simple to end-stopped cells. Vision Research, Vol. 32, pp. 963–981.
Heitger F. (1995). Feature Detection using Suppression and Enhancement. Technical Report BIWI-TR-160, Institute for Communications Technology, Image Science Laboratory, ETH, Zürich, Switzerland.
Henricsson O. and F. Heitger (1994). The Role of Key-Points in Finding Contours. In J.O. Eklundh, editor, Computer Vision — ECCV’94, volume II, pp. 371–383. Springer Verlag, Berlin.
Henricsson O. (1995). Inferring Homogeneous Regions by Combining Contour Relations and Rich Image Attributes. Technical Report BIWI-TR-162, Institute for Communications Technology, Image Science Lab, ETH, Zürich, Switzerland.
Lowe D.G. (1985). Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, Boston, MA.
Mohan R. and R. Nevatia (1992). Perceptual Organization for Scene Segmentation and Description. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14,No. 6,pp. 616–635.
Sumanaweera T.S., G. Healey, B. Lee, T.O. Binford, and J. Ponce (1988). Image Segmentation Using Geometric and Physical Constraints. In DARPA Image Understanding Workshop, pp. 1091–1099, Cambridge, Massachusetts.
Ylä-Jääski A. and F. Ade (1995). Grouping Symmetrical Structures for Object Segmentation and Description. Computer Vision, Graphics, and Image Processing: Image Understanding, Accepted.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Birkhäuser Verlag Basel
About this paper
Cite this paper
Henricsson, O. (1995). Inferring Homogeneous Regions from Rich Image Attributes. In: Gruen, A., Kuebler, O., Agouris, P. (eds) Automatic Extraction of Man-Made Objects from Aerial and Space Images. Monte Verità. Birkhäuser Basel. https://doi.org/10.1007/978-3-0348-9242-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-0348-9242-1_2
Publisher Name: Birkhäuser Basel
Print ISBN: 978-3-0348-9958-1
Online ISBN: 978-3-0348-9242-1
eBook Packages: Springer Book Archive