Title :
Synthesis and transformation of three-dimensional facial images
Author :
Tiddeman, Bernard ; Rabey, Graham ; Duffy, Neil
Author_Institution :
Sch.of Psychol., St. Andrews Univ., UK
Abstract :
In this article, we enhance and extend 2-D methods by using texture-mapped laser-video depth data. Methods for the synthesis of new three-dimensional (3-D) facial images from a database of texture-mapped laser-scanned surfaces are described. Four methods are used to create new facial images. The first constructs average facial images from a sample of faces. The second exaggerates the difference between a subject and an average to create a caricature. The third method captures the difference between two averages, which can then be applied to individuals for statistical transformation. Finally, principal component analysis is used to find the major axes of facial variation in a sample, allowing the construction of completely novel faces from a small vector of values.
Keywords :
covariance analysis; face recognition; feature extraction; image colour analysis; image morphing; image registration; image texture; principal component analysis; rendering (computer graphics); surface fitting; video signal processing; 3D facial images; average construction; average facial images; caricature; colour analysis; covariance matrix; face-space transformations; facial image synthesis; feature extraction; image warping; laser-video depth data; major axes of facial variation; principal component analysis; rendering; sample of faces; statistical transformation; texture-mapped laser-scanned surface data; Biology; Data mining; Feature extraction; Large Hadron Collider; Mouth; Nose; Rendering (computer graphics); Shape; Topology; Age Factors; Algorithms; Cephalometry; Computer Simulation; Databases as Topic; Esthetics; Face; Female; Humans; Image Processing, Computer-Assisted; Male; Sex Factors; Signal Processing, Computer-Assisted; Skin Pigmentation;
Journal_Title :
Engineering in Medicine and Biology Magazine, IEEE
