Generalized quotient image
Published 12 November 2004
Haitao Wang, S.Z. Li, Yangsheng Wang
Citations173
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
Experimental results show that the algorithms presented can significantly improve the performance of face recognition under varying illumination conditions.
Abstract
We present a unified framework for modeling intrinsic properties of face images for recognition. It is based on the quotient image (QI) concept, in particular on the existing works of QI, spherical harmonic, image ratio and retinex. Under this framework, we generalize these previous works into two new algorithms: (1) non-point light quotient image (NPL-QI) extends QI to deal with non-point light sources by modeling non-point light directions using spherical harmonic bases; (2) self-quotient image (S-QI) extends QI to perform illumination subtraction without the need for alignment and no shadow assumption. Experimental results show that our algorithms can significantly improve the performance of face recognition under varying illumination conditions.
Keywords
Computer ScienceEngineering
Journal of Cognitive NeuroscienceEigenfaces for Recognition
13,775 Citations1991Matthew Turk, Alex Pentland
A near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals, and that is easy to implement using a neural network architecture.
IEEE Transactions on Pattern Analysis and Machine IntelligenceFrom few to many: illumination cone models for face recognition under variable lighting and pose
4,915 Citations2001Athinodoros S. Georghiades, Peter N. Belhumeur +1 more
A generative appearance-based method for recognizing human faces under variation in lighting and viewpoint that exploits the fact that the set of images of an object in fixed pose but under all possible illumination conditions, is a convex cone in the space of images.
IEEE Transactions on Image ProcessingA multiscale retinex for bridging the gap between color images and the human observation of scenes
2,966 Citations1997Daniel J. Jobson, Zia Ur Rahman +1 more
This paper extends a previously designed single-scale center/surround retinex to a multiscale version that achieves simultaneous dynamic range compression/color consistency/lightness rendition and defines a method of color restoration that corrects for this deficiency at the cost of a modest dilution in color consistency.
IEEE Transactions on Image ProcessingProperties and performance of a center/surround retinex
2,287 Citations1997Daniel J. Jobson, Zia Ur Rahman +1 more
A practical implementation of the retinex is defined without particular concern for its validity as a model for human lightness and color perception, and the trade-off between rendition and dynamic range compression that is governed by the surround space constant is described.
IEEE Transactions on Pattern Analysis and Machine IntelligenceLambertian reflectance and linear subspaces
1,568 Citations2003Ronen Basri, David W. Jacobs
The CMU Pose, Illumination, and Expression (PIE) database
1,449 Citations2003Terence Sim, Simon Baker +1 more
Between October 2000 and December 2000, a database of over 40,000 facial images of 68 people was collected, using the CMU 3D Room to imaged each person across 13 different poses, under 43 different illumination conditions, and with four different expressions.
An efficient representation for irradiance environment maps
775 Citations2001Ravi Ramamoorthi, Pat Hanrahan
A simple and efficient procedural rendering algorithm amenable to hardware implementation, a prefiltering method up to three orders of magnitude faster than previous techniques, and new representations for lighting design and image-based rendering are considered.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe quotient image: class-based re-rendering and recognition with varying illuminations
618 Citations2001Amnon Shashua, Tammy Riklin Raviv
It is shown that a small database of objects is sufficient for generating the image space with varying illumination of any new object of the class from a single input image of that object.
What is the set of images of an object under all possible lighting conditions?
384 Citations1996Peter N. Belhumeur, David Kriegman
It is proved that the set of n-pixel images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a conveX polyhedral cone in IR/sup n/ and that the dimension of this illumination cone equals the number of distinct surface normals.
Journal of the Optical Society of America AOn the relationship between radiance and irradiance: determining the illumination from images of a convex Lambertian object
377 Citations2001Ravi Ramamoorthi, Pat Hanrahan
This work derives a simple closed-form formula for the irradiance in terms of spherical harmonic coefficients of the incident illumination and demonstrates that the odd-order modes of the lighting with order greater than 1 are completely annihilated, contradicting a theorem that is due to Preisendorfer.
Lecture notes in computer scienceAn Image Preprocessing Algorithm for Illumination Invariant Face Recognition
344 Citations2003Ralph Gross, V. Brajovic
This work proposes a new image preprocessing algorithm that compensates for illumination variations in images from a single brightness image, which does not require any training steps, knowledge of 3D face models or reflective surface models, and demonstrates large performance improvements.
A low-dimensional representation of human faces for arbitrary lighting conditions
293 Citations1994Hallinan
A low-dimensional model for human faces is proposed that can both synthesize a face image when given lighting conditions and can estimate lighting conditions when given a face images.
Lambertian reflectance and linear subspaces
276 Citations2002Ronen Basri, David Jacobs
It is proved that the set of all reflectance functions (the mapping from surface normals to intensities) produced by Lambertian objects under distant, isotropic lighting lies close to a 9D linear subspace, implying that the images of a convex Lambertian object obtained under a wide variety of lighting conditions can be approximated accurately with a low-dimensional linear sub space.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAnalytic PCA construction for theoretical analysis of lighting variability in images of a Lambertian object
232 Citations2002Ravi Ramamoorthi
This work analytically constructs the principal component analysis for images of a convex Lambertian object, explicitly taking attached shadows into account, and finds the principal eigenmodes and eigenvalues with respect to lighting variability, and extends these results to the single-viewpoint case.
Illumination cones for recognition under variable lighting: faces
214 Citations2002Athinodoros S. Georghiades, David Kriegman +1 more
This method is both an implementation and extension (an extension in that it models cast shadows) of the illumination cone representation proposed in Belhumeur and Kriegman (1996), and the results exceed those of popular existing methods.
International Journal of Computer VisionReflectance based object recognition
186 Citations1996Shree K. Nayar, Ruud M. Bolle
An algorithm is developed that estimates a reflectance ratio for each region in an image with respect to its background that is efficient as it computes ratios for all image regions in just two raster scans.
5±2 eigenimages suffice: an empirical investigation of low-dimensional lighting models
177 Citations2002Russell A. Epstein, Peter W. Hallinan +1 more
It is found that sharp specularities and shadows cannot be well represented by a low dimensional model, but both effects can be adequately described as residuals to such a model.
Comparing images under variable illumination
132 Citations2002David W. Jacobs, Peter N. Belhumeur +1 more
It is shown that for point sources and objects with Lambertian reflectance, the ratio of two images from the same object is simpler than the ratios of images from different objects.
The quotient image: Class based recognition and synthesis under varying illumination conditions
79 Citations2003Tammy Riklin Raviv, Amnon Shashua
The key result in this approach is based on a definition of an illumination invariant signature image, which enables an analytic generation of the image space with varying illumination from a single input image and a very small sample of other objects of the class-in the authors' experiments as few as two objects.