The Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations

By Amnon Shashua, Tammy Riklin-Raviv. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001

681 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/219fd359c33cc072a46788d82ee64513356bc285

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a Single Image (2019, methodology): “This compositing procedure utilizes the idea of ratio (or quotient images) that has been used in the past for relighting [42, 50].”
Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain (2006, background): “In [ 12 ], the quotient image is regarded as the illumination invariant signature image which can be used for face recognition under varying lighting conditions.”
Toward Guaranteed Illumination Models for Non-convex Objects (2013, methodology): “Various approaches have been proposed to mitigate this problem, for example using nonlinear features based on gradient orientation [13], using quotient images [18] or total variation regularization [6].”
Illumination Invariant Face Recognition Using Near-Infrared Images (2007, background): “Shashua and Raviv [26] proposed a simple yet practical algorithm, called the quotient image, for extracting illumination invariant representation.”
Age Synthesis and Estimation via Faces: A Survey (2010, background): “An interesting idea, so-called Merging Ratio Images (MRI) [88], is to extend the Ratio Image (RI) concept to multiple face attributes and merge expression RI [89], illumination RI (quotient image) [90], and aging RI [91] for photorealistic face rendering.”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 3d Face Reconstruction from a Single Image Using a Single Reference Face Shape (neutral): “Another method [29] renders faces in novel views by making the restrictive assumption that different faces share the exact same shape while they differ only in albedo.”
Face recognition under varying lighting conditions using self quotient image (2004, methodology): “Recent years, many algorithms have been proposed; let us highlight three major approaches of lighting modeling for 3D object recognition: as Illumination Cone [1]-[3], Quotient Image [4][5], and Spherical Harmonic Subspace [6-10].”
Face Recognition Under Varying Illumination Using Gradientfaces (2009, background): “Quotient image (QI) [19] is regarded as an illumination invariant and designed for dealing with illumination variation in face recognition.”
Digital photography with flash and no-flash image pairs (2004, background): “The ratio captures the local detail variation in F and is commonly called a quotient image [Shashua and Riklin-Raviv 2001] or ratio image [Liu et al. 2001] in computer vision.”
Illumination normalization for robust face recognition against varying lighting conditions (2003, background): “Most recently, the Quotient image [23] is reported to be invariant to illumination and may be used to recognize faces when lighting conditions change.”