Pose-Encoded Spherical Harmonics for Robust Face Recognition Using a Single Image

TitlePose-Encoded Spherical Harmonics for Robust Face Recognition Using a Single Image
Publication TypeBook Chapters
Year of Publication2005
AuthorsYue Z, Zhao W, Chellappa R
EditorZhao W, Gong S, Tang X
Book TitleAnalysis and Modelling of Faces and GesturesAnalysis and Modelling of Faces and Gestures
Series TitleLecture Notes in Computer Science
Pagination229 - 243
PublisherSpringer Berlin / Heidelberg
ISBN Number978-3-540-29229-6

Face recognition under varying pose is a challenging problem, especially when illumination variations are also present. Under Lambertian model, spherical harmonics representation has proved to be effective in modelling illumination variations for a given pose. In this paper, we extend the spherical harmonics representation to encode pose information. More specifically, we show that 2D harmonic basis images at different poses are related by close-form linear combinations. This enables an analytic method for generating new basis images at a different pose which are typically required to handle illumination variations at that particular pose. Furthermore, the orthonormality of the linear combinations is utilized to propose an efficient method for robust face recognition where only one set of front-view basis images per subject is stored. In the method, we directly project a rotated testing image onto the space of front-view basis images after establishing the image correspondence. Very good recognition results have been demonstrated using this method.