Related Concepts
Definition
A set of images used to represent characteristics of a scene pictured in an image, with each image representing one particular characteristic of the scene.
Background
Vision systems have been categorized into low- and high-level processing, with high-level processing taking an object-centered approach [1]. In this categorization, the role of low-level processing is to extract basic characteristics at all locations in the image. These characteristics are then used to find objects.
Intrinsic images are a method for representing the low-level characteristics extracted from images. In the intrinsic image representation, proposed by Barrow and Tenenbaum in [2], one image represents each of the characteristics being used in the system. The value of each pixel represents the value of the characteristic at each point in the scene.
These images show an example of an intrinsic image decomposition. In this decomposition,...
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Szeliski R (1990) Bayesian modeling of uncertainty in low-level vision. Int J Comput Vis 5(3):271–301
Barrow HG, Tenenbaum JM (1978) Recovering intrinsic scene characteristics from images. In: Hanson A, Riseman E (eds) Computer vision systems. Academic, New York, pp 3–26
Weiss Y (2001) Deriving intrinsic images from image sequences. In: The proceedings of the IEEE international conference on computer vision, Vancouver, pp 68–75
Tappen MF, Freeman WT, Adelson EH (2005) Recovering intrinsic images from a single image. IEEE Trans Pattern Anal Mach Intell 27(9):1459–1472
Tappen MF, Adelson EH, Freeman WT (2006) Estimating intrinsic component images using non-linear regression. In: The Proceedings of the 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR), vol 2. IEEE Computer Society, Los Alamitos, pp 1992–1999
Hoiem D, Efros AA, Hebert M (2008) Closing the loop on scene interpretation. in: Proceedings the IEEE conference on computer vision and pattern recognition (CVPR). IEEE, Piscataway
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this entry
Cite this entry
Tappen, M.F. (2014). Intrinsic Images. In: Ikeuchi, K. (eds) Computer Vision. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-31439-6_245
Download citation
DOI: https://doi.org/10.1007/978-0-387-31439-6_245
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30771-8
Online ISBN: 978-0-387-31439-6
eBook Packages: Computer ScienceReference Module Computer Science and Engineering