Abstract
In this Letter, a new methodology for Colour Shape From Shading problem is proposed. The problem of colour SFS refers to the well-known fact that most real objects usually contain mixtures of diffuse and specular colour reflections. In this paper, these limitations are addressed and a new colour neural based model is proposed. The proposed approach focuses on developing a generalized neural based colour reflectance model. Experimental results on synthetic coloured objects and a real coloured object were performed to demonstrate the performance of the proposed methodology.
Similar content being viewed by others
References
Bui-Tuong, P.: 'Illumination for computer generated pictures', Comm. ACM, 18(6) June (1975), 311–317
Cho, S. Y. and Chow, T. W. S.: 'Shape recovery from shading by a new neural based reflectance model', IEEE Transaction on Neural Networks, 10(6) (1999), 1536–1541
Cho, S. Y. and Chow, T. W. S.: 'Learning parametric specular re.ectance model by radial basis function networks', IEEE Transaction on Neural Networks, 17(6) December (2000), 1346–1350.
Cho, S. Y. and Chow, T. W. S.: 'Training Multilayer Neural Networks Using Fast Global Learning Algorithm-Least Squares and Penalized Optimization Methods', Neurocomputing, 25(1–3) (1999), 115–131.
Cho, S. Y. and Chow, T. W. S.: 'Enhanced 3D Shape Recovery Using Neural Based Hybrid Reflectance Model', Neural Computation, accepted to be published, 2001.
Christensen, P. H. and Shapiro, L. G.: Three-Dimensional shape from color photometric stereo', International Journal of Computer Vision, 13:2 (1994), 213–227.
Hornik, K., Stinchcombe M. and White H.: 'Multilayer feedforward network are universal approximation', Neural Networks, 2 (1989), 359–366.
Ikeuchi, and Horn, 'Numerical shape from shading and occluding boundaries', Artificial Intelligence, 17(1–3) (1981), 141–184.
Klinker, G. J., Shafer S. A. and Kanade T.: 'A physical approach to color image understanding', Intl. J. Comp. Vision, 7 (1990), 7–38.
Lee, K. M. and Kuo C.-C. J.: 'Shape from Shading with a Generalized Reflectance Map Model', Computer Vision and Image Understanding, 67(2) (1997), 143–160.
Nayar, S. K., Ikeuchi, K. and Kanade, T.: 'Determining Shape and Reflectance of Hybrid Surface by Photometric Sampling', IEEE Transaction on Robotics and Automation, 6(4) 1990, 418–430.
Novak, C. L. and Shafer, S. A.: 'Anatomy of a histogram' In: Proc. Conf. Comp. Vision Pat. Recog., June (1992), 599–605.
Park, J. and Sandberg, I. W.: 'Universal Approximation Using Radial Basis Function Networks', Neural Computation, 3 (1991), 261–275.
Tian, Y.-L. and Tsui. H. T.: 'Shape from Shading for Non-Lambertian Surfaces from One Color Image', IEEE Proceedings of ICPR'96, (1996), 258–262.
Torrance, K. E. and Sparrow, E. M.: 'Theory for off-specular reflection from roughened surfaces', Journal of Optical of America, 57 (1967), 1105–1114.
Ward, G. J.: 'Measuring and modeling anisotropic reflection', Comp. Graphics, 26(2) July (1992), 265–272. Proceedings ACM Siggraph '92.
Warnock, J.: A Hidden-Surface Algorithm for Computer Generated Half-Tone pictures, Technical Report TR 4–15, NTIS AS-753 671, Computer Science Department, University of Utah, Salt Lake City, UT, June 1969.
Zheng, Q. and Chellappa, 'Estimation of Illuminant Direction, Albedo, and Shape From Shading', IEEE Transaction on Pattern Analysis and Machine Intelligence, 13(7) (1991), 680–702.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Cho, SY., Chow, T.W.S. & Ng, K.T. Shape From Shading by Using Neural Based Colour Reflectance Model. Neural Processing Letters 16, 121–136 (2002). https://doi.org/10.1023/A:1019961024404
Issue Date:
DOI: https://doi.org/10.1023/A:1019961024404