Color invariance
IEEE Transactions on Pattern Analysis and Machine IntelligencePublished 1 January 2001
Jan‐Mark Geusebroek, R. van den Boomgaard, A.W.M. Smeulders, Hugo Geerts
Citations535
SJR quartileQ1
SJR score3.91
SNIP5.99
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The Gaussian scale-space paradigm for color images is exploited to define a framework for the robust measurement of object reflectance from color images, and the proposed invariants are considered more adequate for the measurement of invariant color features than existing methods.
Abstract
This paper presents the measurement of colored object reflectance, under different, general assumptions regarding the imaging conditions. We exploit the Gaussian scale-space paradigm for color images to define a framework for the robust measurement of object reflectance from color images. Object reflectance is derived from a physical reflectance model based on the Kubelka-Munk theory for colorant layers. Illumination and geometrical invariant properties are derived from the reflectance model. Invariance and discriminative power of the color invariants is experimentally investigated, showing the invariants to be successful in discounting shadow, illumination, highlights, and noise. Extensive experiments show the different invariants to be highly discriminative, while maintaining invariance properties. The presented framework for color measurement is well-founded in the physics of color as well as in measurement science. Hence, the proposed invariants are considered more adequate for the measurement of invariant color features than existing methods.
Keywords
Computer ScienceEngineeringPhysics and Astronomy
Physics BulletinColor Science, Concepts and Methods. Quantitative Data and Formulas
3,554 Citations1967W. D. Wright
The authors' aim has been to provide a comprehensive source book of data required by the practical and theoretical worker in the field of colour and they have achieved this aim so successfully that their book is likely to become the standard work on the subject and to remain so for a good many years.
Journal of the Optical Society of AmericaNew Contributions to the Optics of Intensely Light-Scattering Materials Part I
2,594 Citations1948Paul Kubelka
Biological CyberneticsThe structure of images
2,406 Citations1984Jan J. Koenderink
It is shown that any image can be embedded in a one-parameter family of derived images (with resolution as the parameter) in essentially only one unique way if the constraint that no spurious detail should be generated when the resolution is diminished, is applied.
Scale-Space Theory in Computer Vision
2,148 Citations1994Tony Lindeberg
Computer Vision Graphics and Image ProcessingA note on the gradient of a multi-image
940 Citations1986Silvano Di Zenzo
Gradient based edge detection techniques can be extended to multispectral images in various ways: difference operators can be applied to each component of a multi-image, and the results can be combined, e.g., taking the RMS or the sum, or the maximum of their absolute values.
Color-based object recognition
819 Citations1998
Optica Acta International Journal of OpticsColor in Business, Science and Industry
750 Citations1976A.W.S. Tarrant
Journal of the Optical Society of America AEvaluation of linear models of surface spectral reflectance with small numbers of parameters
741 Citations1986Laurence T. Maloney
The results suggest that constraints on possible surface-reflectance functions and the "filtering" properties of the shapes of the spectral-sensitivity curves of photoreceptors can both contribute to color constancy.
Archives of OphthalmologyOutlines of a Theory of the Light Sense.
509 Citations1965Arthur Linksz
One cannot, of course, expect that this translation of Hering's work will ever accomplish what Southall's translation of the "Handbook of Physiological Optics" did for the spreading of the Helmholtzian gospel within the English reading community of scientists.
IEEE Transactions on Image ProcessingAnisotropic diffusion of multivalued images with applications to color filtering
444 Citations1996Guillermo Sapiro, Dario L. Ringach
A general framework for anisotropic diffusion of multivalued images is presented and the proposed framework is applied to the filtering of color images represented in CIE-L*a*b* space.
Image and Vision ComputingScale and the differential structure of images
386 Citations1992Luc Florack, Bart M. ter Haar Romeny +2 more
This paper shows why the operations of scaling and differentiation cannot be separated and permits us to construct in a systematic way multiscale, cartesian differential invariants, i.e. true image descriptors that exhibit manifest invariance with respect to a change of cartesian coordinates.
CVGIP Graphical Models and Image ProcessingEdge detection in multispectral images
272 Citations1991Aldo Cumani
An extension of edge detectors based on second-order differential operators to the case of multiple band (color) images is proposed, and a local directional measure of multispectral contrast is defined.
Applied SpectroscopyColor in Business Science and Industry
247 Citations1953Deane B. Judd, George L. Buc
Biological CyberneticsReceptive field families
183 Citations1990Jan J. Koenderink, Andrea J. van Doorn
Journal of the Optical Society of America AUsing color for geometry-insensitive segmentation
145 Citations1989Glenn Healey
This work shows that approximate reflectance models exist that preserve much of the structure of the more-detailed models, and shows that Shafer’s dichromatic reflection model is a reasonable approximation for a large class of inhomogeneous dielectrics.
Journal of the Optical Society of America AAmbient illumination and the determination of material changes
115 Citations1986Ron Gershon, Allan D. Jepson +1 more
It is shown that, given some knowledge about the strength of the ambient illumination, this method provides a better classification of shadow boundaries and material changes.
Journal of Mathematical Imaging and VisionCartesian differential invariants in scale-space
91 Citations1993Luc Florack, Bart M. ter Haar Romeny +2 more
A “diagrammar” of differential invariants and tensors is proposed, i.e., a diagrammatic representation of image derivatives in scale-space together with a set of simple rules for representing meaningful local image properties.
Lecture notes in computer scienceColor and Scale: The Spatial Structure of Color Images
86 Citations2000Jan‐Mark Geusebroek, R. van den Boomgaard +2 more
This work considers a Gaussian color model, which inherently uses the spatial and color information in an integrated model, and proposes a framework for spatial color measurement, based on the Gaussian scale-space theory.
Computational imaging and visionDifferential Invariant Signatures and Flows in Computer Vision: A Symmetry Group Approach
86 Citations1994Peter J. Olver, Guillermo Sapiro +1 more
This work gives a modern approach to the theory of differential invariants, describing concepts like Lie theory, jets, and prolongations and presents a high level way of defining invariant geometric flows for a given Lie group.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRetrieving multispectral satellite images using physics-based invariant representations
58 Citations1996Glenn Healey, Anil K. Jain
A set of algorithms and a search strategy for the robust content-based retrieval of multispectral satellite images using representations and methods that are invariant to illumination and atmospheric conditions are presented.
Detection and Classification of Hyper-Spectral Edges
38 Citations1999H.M.G. Stokman, Theo Gevers
An edge classifier is derived which distinguishes hyper-spectral edges into the following types: a shadow or geometry edge, a highlight edge, and a material edge.
Spectral gradient: a material descriptor invariant to geometry and incident illumination
38 Citations1999Elli Angelopoulou, S.W. Lee +1 more
A novel methodology is presented which extracts reflectivity information of the various materials in the scene independent of incident light and scene geometry, a material descriptor which is invariant to scene geometry and incident illumination for smooth diffuse surfaces.
Color Invariant Snakes
32 Citations1998Theo Gevers, S. Ghebreab +1 more
This paper aims at using color invariant gradient information to guide the deformation process to obtain snake boundaries which correspond to material boundaries in images discounting the disturbing influences of surface orientation, illumination, shadows and highlights.
Measurement of color invariants
19 Citations2002Jan‐Mark Geusebroek, A.W.M. Smeulders +1 more
The Gaussian scale-space paradigm is exploited to define framework for the robust measurement of object reflectance from color images, showing the invariants to be successful in discounting shadow, illumination intensity, highlights, and noise.
Lecture notes in computer scienceColor Invariant Edge Detection
17 Citations1999Jan‐Mark Geusebroek, Anuj Dev +4 more
Reflectance-based classification of color edges
9 Citations2003Gevers
A novel approach to color edge detection by automatic noise-adaptive thresholding derived from sensor noise analysis is proposed and a taxonomy on color edge types is presented, obtaining a parameter-free edge classifier.