ICANN ’94 pp 62-65 | Cite as

Hybrid Methods for Robust Irradiance Analysis and 3-D Shape Reconstruction from Images

  • F. Callari
  • U. Maniscalco
  • P. Stomiolo
Conference paper


The analysis of the differential structure of images is an interesting task in machine vision, among other reasons because it can provide relevant featural representation of images, suited for higher level information processing task like geometry reconstruction and object recognition. The importance of invariants of the field of isophotae on lambertian surfaces in shape perception by means of chiaroscuro is discussed in (Koenderink and Van Doom, 1980). In their approach to shape from shading, (Breton et al, 1992) represent the shading of the image by means of its shading flow field, i.e. by the first order differential structure of the image expressed as the isoluminance direction and gradient magnitude. The (Grossberg and Mingolla, 1985) model of low level visual processes uses input sensors approximately sensitive to brightness gradient, providing a map of segments oriented along constant brightness lines.


Shape Perception Detector Orientation Vectorial Composition Brightness Gradient Geometry Reconstruction 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Ardizzone, E.,Chella, A., Pirrone, R., Sorbello, F.: A System Based on Neural Architectures for the Reconstruction of 3-D Shapes from Images. In: Ardizzone, E., Gaglio, S. Sorbello, F. (ed.s), Trends in Artificial Intelligence Springer-Verlag, Berlin, 1991.Google Scholar
  2. Barr, A. H.: Superquadrics and AnglePreserving Transformations, IEEE Computer Graphics and Applications 1, 11–23, 1981CrossRefGoogle Scholar
  3. Breton, P., Iverson, L. A., Langer, M. SZucker, S. W.: A New Approach to Shape from Shading. In: Carpenter, G., Grossberg, S. (eds.): Neural Networks for Vision and Image Processing Bradford Book, MIT Press, Cambridge, 1992Google Scholar
  4. Callari, F. G., Maniscalco, U., Stomiolo, P.: Robust Shading Flow Estimation and Applications to Parameric Surface Recovery, CS &. AI Lab. Tech. Report. 9/1/1993, Elec. Eng. Dept., Univ. of Palenno, Italy.Google Scholar
  5. Grossberg, S. Mingolla, E.: Computer Simulations of Neural Networks for Perceptual Psychology. Behavior Research Methods,lnstruments, and Computers 18 (6), 601–607, 1986.CrossRefGoogle Scholar
  6. Hom, B.: Robot Vision MIT Press, Cambridge, Mass, 1986.Google Scholar
  7. Koenderink, J. J., Van Doom, A.:Pholometric Invariances Related to Solid Shape, Optica Acta, 27 (7), 981–996,1980.CrossRefMathSciNetGoogle Scholar
  8. Maniscalco, U., Pirrone, R., Sorbello, F., Stomiolo, P: A Shape From Shading Hybrid Approach to Estimate Superquadric Parameters. In: Caianiello, E. R. (ed.), Proceedings of Sixth Italian Workshop on Parallel. Architectures and Neural Networks, World Scientific Publ. Co, Singapore, 1993.Google Scholar
  9. Pentland, A.: Finding the Illummant Direction, J. Opt.Soc. Amer., 72, 448–455, 1982CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1994

Authors and Affiliations

  • F. Callari
    • 1
    • 2
  • U. Maniscalco
    • 1
  • P. Stomiolo
    • 1
  1. 1.DIE- Dipartimento di Ingegneria ElettricaUniversity of Palermo Viale delle ScienzePalermoItaly
  2. 2.DIE and Computer Science DeptUniversity of Colorado at BoulderBoulderUSA

Personalised recommendations