Abstract
This paper describes an image segmentation and analysis technique based on three-dimensional information gathered by means of the stereo-photometric approach. It allows the measure of the attitude and area of surfaces whose optical properties are known. After a brief summary of the stereo-photometric theory and the description of the Extended Gaussian Image (EGI), we face the problem of the segmentation of the scene, by giving a solution based on the computation of the EGI. The results of the segmentation are then translated to a symbolical form in order to be interpreted by a tiny Prolog-written expert system.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
6. References
B.K.P. Horn, K. Ikeuchi, Understanding Image Intensity, Artificial Intelligence 8, 1977, pp. 201–231.
R.J. Woodman, Photometric Method for Determining Surface Orientation from Multiple Images, Optical Engineering 19 (1), Jan.–Feb. 1980, pp.139–144.
L. Carrioli, M. Diani, Segmentazione fotometrica di scene 3-D attraverso l'Immagine Gaussiana Estesa, Rivista di Informatica, Vol. XVII, n. 4, Oct.–Dec. 1987, pp. 279–289.
B.K.P. Horn, Extended Gaussian Image, Proc. IEEE, Dec. 1984, pp. 1671–1678.
K. Ikeuchi, Determining Surface Orientation of Specular Surfaces by Using the Photometric Stereo Method, IEEE Trans. on PAMI 3 (6), 1981, pp. 661–669.
V. Cantoni, M. Ferretti, S. Levialdi, R. Stefanelli, PAPIA: Pyramidal Architecture for Parallel Image Analysis, Proc. 7th Symp. on Computer Arithmetic, Urbana (Illinois), 1985, pp. 237–242.
B.T. Phong, Illumination for Computer generated Images, Comm. ACM 18(6), June 1975, pp. 311–317.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1989 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Carrioli, L., Cei, U., Diani, M. (1989). Recognition of polyhedra by photometric stereo. In: Cantoni, V., Creutzburg, R., Levialdi, S., Wolf, G. (eds) Recent Issues in Pattern Analysis and Recognition. Lecture Notes in Computer Science, vol 399. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-51815-0_57
Download citation
DOI: https://doi.org/10.1007/3-540-51815-0_57
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-51815-0
Online ISBN: 978-3-540-46815-8
eBook Packages: Springer Book Archive