Abstract
Shape from Shading is perhaps the most difficult topic to deal with in Artificial Vision: several researchers have faced it using different approaches. The most part of these methods are based on the Horn algorithm so they require very heavy regularity assumptions about the perceived objects' shape and are computationally expensive.
The use of neural networks may be a good solution to the drawbacks of the classical approaches to SFS: in fact a neural network is able to solve estimation problems through a process of learning from a few meaningful examples requiring a very low computational cost.
Two different neural approaches are proposed by the authors: the first one consists of a cascaded architecture made up by a first stage named BWE (Boundary Webs Extractor) which is aimed to extract a brightness gradient map from the image, followed by a backpropagation network that estimates the geometric parameters of the object parts present in the acquired scene. The second approach is based on the extraction of the boundary webs map from the image and its comparison with boundary webs maps exhaustively generated from synthetic superquadrics. A purposely defined error figure has been used to find the best match between the two kinds of maps.
A functional comparison between the two systems is described and the quite satisfactory experimental results are presented.
Preview
Unable to display preview. Download preview PDF.
References
Ardizzone, E., Gaglio, S., Sorbello, F. (1989). Geometric and Conceptual Knowledge Representation within a Generative Model of Visual Perception, Journal of Intelligent and Robotic Systems, 2, 381–409.
Ardizzone, E., Chella, A., Compagno, G., Pirrone, R. (1992). An Efficent Neural Architecture Implementing the Boundary Contour System, in: Aleksander, I., Taylor, J. (eds.) Artificial Neural Networks, 2. North-Holland, Amsterdam.
Ardizzone, E., Chella, A., Gaglio, S., Pirrone, R., Sorbello, F. (1991), A Neural Architecture for the Estimate of 3-D Shape Parameters, in: Caianiello, E. (ed.): Parallel Architectures and Neural Networks — Fourth Italian Workshop, World Scientific Publishers, Singapore (in press).
Ardizzone, E., Chella, A., Pirrone, R., Sorbello, F. (1991), A System Based on Neural Architectures for the Reconstruction of 3-D Shapes from Images, in: Ardizzone, E., Gaglio, S., Sorbello, F. (eds.): Trends in Artificial Intelligence, Springer Verlag, Berlin.
Barr, A.H. (1981). Superquadrics and Angle-Preserving Transformations, IEEE Computer Graphics and Applications, 1, 11–23.
Callari, F., Chella, A., Gaglio, S., Pirrone, R. (1992). A New Hybrid Approach to Robot Vision, in: Aleksander, I., Taylor, J. (eds.) Artificial Neural Networks, 2. North-Holland, Amsterdam.
Grossberg, S., Mingolla, E., (1987). Neural Dynamics of Surface Perception: Boundary Webs, Illuminants, and Shape-from-Shading. Computer Vision, Graphics and Image Processing, 37, 116–165.
Hecht-Nielsen,R.(1990) Neurocomputing, Addison-Wesley, Reading,MA,USA.
Horn, B.K.P. (1986). Robot Vision. MIT Press, Cambridge, MA, USA.
Marr, D.(1982) Vision, Freeman and Co., New York.
Pentland, A.P., Perceptual Organization And The Representation Of Natural Form, Artificial Intelligence, 28, 293–331, 1986.
Rumelhart,D.E., Hinton,G.E.&Williams,R.J.,Learning Internal Representations by Error Propagation, in: Rumelhart, D. E., McClelland, J. L. (ed.s) & PDP Research Group (1986), Parallel Distributed Processing, Vol 1, MIT Press, Cambridge, MA, USA.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Chella, A., Gaglio, S., Pirrone, R. (1993). New shape from Shading methods. In: Roberto, V. (eds) Intelligent Perceptual Systems. Lecture Notes in Computer Science, vol 745. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57379-8_7
Download citation
DOI: https://doi.org/10.1007/3-540-57379-8_7
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57379-1
Online ISBN: 978-3-540-48103-4
eBook Packages: Springer Book Archive