Abstract
To produce realistic synthetic images, it is important to shade objects based on real illumination conditions of a scene. Estimating the direction of the light source of the scene is a key factor to achieve this. Properly estimating this source under noisy conditions is very challenging, and it is a subject of intense research. Computational intelligence techniques offer promising way of tackling this problem. This paper presents a novel neural network-based approach for recovering light source direction in relation to the viewpoint direction of a graphical image in noisy environments. The estimated light source direction can be used for the generation of 3D images from 2D ones. Experiments are performed using both synthetic and real images in noisy scenes. Four synthetic surfaces where generated with varying light source directions for a total of 12 images. Three real images were also used with varying degrees of noise. The experimental results show that the proposed approach is robust and provides a good level of accuracy.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Ecker A, Jepson AD (2010) Polynomial shape from shading. In: Proceedings of IEEE international conference on computer vision and pattern recognition (CVPR), 13–18 June 2010, pp 145–152
Zhang R, Tsai PS, Cryer JE, Shah M (1999) Shape from shading: a survey. Trans Pattern Anal Mach Intell 21(8):690–706
Zoran D, Krishnan D, Bento J, Freeman B (2014) Shape and illumination from shading using the generic viewpoint assumption. In: Advances in neural information processing systems (NIPS 2014)
Martnez H, Laukkanen S (2015) Towards an augmented reality guiding system for assisted indoor remote vehicle navigation. EAI Endor Trans Ind Netw Intell Syst 15(2):e3
Zhou SM, Li HX, Xu LD (2003) A variational approach to intensity approximation for remote sensing images using dynamic neural networks. Expert Syst 20(4):163–170
Gibbins D, Brooks MJ, Chojnacki W (1995) Determining light-source direction from images of shading. In: Perspectives on cognitive science: theories, experiments and foundations, chap 9, pp 127–144. Ablex Publishing Corporation, Norwood
Bouganis C-S, Brookes M (2007) Statistical multiple light source detection. IET Comput Vis 1(2):79–91
Bouganis C-S, Brookes M (2004) Multiple light source detection. IEEE Trans Pattern Anal Mach Intell 26(4):509–514
Hougen DR, Ahuja N (1993) Estimation of the light source distribution and its use in integrated shape recovery from stereo and shading. In: IEEE 4th international conference on computer vision, pp 148–155
Ramamoorthi R, Hanrahan P (2001) On the relationship between radiance and irradiance: determining the illumination from images of a convex lambertian object. J Opt Soc Am A 18(10):2448–2459
Ramamoorthi R, Hanrahan P (2001) Analysis of planar light fields from homogeneous convex curved surfaces under distant illumination. In: Proceedings of the SPIE, human vision and electronic imaging, pp 185–198
Ramamoorthi R, Hanrahan P (2001) A signal processing framework for inverse rendering. In: Proceedings of the SIGGRAPH conference, pp 117–128
Kin Chow Chi, Yin Yuen Shiu (2010) A solution to illumination direction estimation of a shaded image: genetic algorithm. Image Vis Comput 28(12):1717–1730
Zhang Zheng, Song Guozhi, Wu Jigang (2014) A novel two-stage illumination estimation framework for expression recognition hindawi publishing corporation. Sci World J 2014:12:565389. doi:10.1155/2014/565389
Debevec P (1998) Rendering synthetic objects into real scenes: bridging traditional and image-based graphics with global illumination and high dynamic range photography. In: Proceedings of the SIGGRAPH, pp 189–198
Gibbins D (1994) Estimating illumination conditions for shape from shading. PhD thesis, Flinders University of South Australia, Australia, May 1994
Pentland AP (1982) Finding the illuminant direction. J Opt Soc Am 72:448–455
Lee CH, Rosenfeld A (1985) Improved methods of estimating shape from shading using the light source coordinate system. Artif Intell 26:125–143
Chojnacki W, Brooks MJ, Gibbins D (1994) Revisiting pentland’s estimator of light source direction. J Opt Soc Am A Opt, Image Sci, Vis 11(1):118–124
Zheng Q, Chellappa R (1991) Estimation of illuminant direction, albedo, and shape from shading. IEEE Trans Pattern Anal Mach Intell 13(7):680–702
Sinha P, Adelson E (1993) Recovering reflectance and illumination in a world of painted polyhedra. In: IEEE 4th international conference on computer vision, pp 156–163
Sato I, Sato Y, Ikeuchi K (1999) Illumination distribution from shadows. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 306–312, June 1999
Sato I, Sato Y, Ikeuchi K (1999) Illumination distribution from brightness in shadows: adaptive estimation of illumination distribution with unknown reflectance properties in shadow regions. In: Proceedings of the IEEE conference on computer vision, pp 875–882
Hara K, Nishino K, Ikeuchi K (2005) Light source position and reflectance estimation from a single view without the distant illumination assumption. IEEE Trans Pattern Anal Mach Intell 27(4):493–505
Elizondo D, Zhou S, Chrysostomou C (2008) Surface reconstruction techniques using neural networks to recover noisy 3d scenes. In: Artificial neural networks-ICANN 2008, pp 857–866. Springer
Grimson W (1981) From images to surfaces: a computational study of the human early visual system. MIT Press, Cambridge
Klette R, Schluns R, Koscha A (1988) Computer vision: three-dimensional data from images. Springer, Singapore
Rumelhart D, Hinton G, Williams R (1988) Learning representations by back-propagating errors. Cognit Model 5:3
Rumelhart DE, Hinton GE, Williams RJ (1988) Learning internal representations by error propagation. In: Anderson JA, Rosenfeld E (eds) Neurocomputing: foundations of research. MIT Press, Cambridge, pp 673–695
Werbos PJ (1974) Beyond regression: new tools for prediction and analysis in the behavioral sciences. PhD thesis, Harvard University, Cambridge
Ascher UM, Carter PM (1993) A multigrid method for shape from shading. NSIAM J Numer Anal 30(1):102–115
Zhang R, Tsai P, Cryer J, Shah M (1997) A survey of shape from shading methods. Technical report CS-TR-97-15, University of Central Florida
Masters T (2014) Practical neural network recipes in C++. Morgan Kaufmann Publishers, US
van Dam Andries, Feiner SK, Hughes JF (1990) Computer Graphics: Principles and Practice. Addison Wesley, Reading
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Elizondo, D.A., Zhou, SM. & Chrysostomou, C. Light source detection for digital images in noisy scenes: a neural network approach. Neural Comput & Applic 28, 899–909 (2017). https://doi.org/10.1007/s00521-016-2281-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2281-0