Prediction of Individual Non‐Linear Aging Trajectories of Faces

Abstract

Represented in a Morphable Model, 3D faces follow curved trajectories in face space as they age. We present a novel algorithm that computes the individual aging trajectories for given faces, based on a non-linear function that assigns an age to each face vector. This function is learned from a database of 3D scans of teenagers and adults using support vector regression. To apply the aging prediction to images of faces, we reconstruct a 3D model from the input image, apply the aging transformation on both shape and texture, and then render the face back into the same image or into images of other individuals at the appropriate ages, for example images of older children. Among other applications, our system can help to find missing children

Three-dimensional human facial morphologies as robust aging markers

“…In this study, we provided a comprehensive and systematic analysis on 3D facial morphology for more than 300 individuals of a wide age range from 17 to 77 years old. Scherbaum et al [28] used 3D facial scans from 95-month-old children to 360-month-old young adults to learn how children faces grow based on a nonlinear model. Facial changes during early development and aging are very different.…”

Fast Face Detector Training Using Tailored Views

“…We do not require initial facial input images, but randomly generate artificial faces while controlling the data variability. Moreover, we introduce facial attributes such as body weight or skin tone and make use of an advanced face model [3] to render the subjects' ages. We also show that our approach is suitable to adjust rendering parameters to particular illumination and pose constraints of given surveillance cameras ( Figure 8).…”

“…By deploying a statistically driven face model for data generation, one can be sure to incorporate the full data variance (with respect to the database of the face model). We use this technique in the following section to first generate randomized 3D faces using a 3D morphable face model [2,3]. In a second step, we modulate these three-dimensional random faces by applying facial attributes, which we then render for defined viewing angles and illumination parameters.…”

“…Modeling To generate artificial training data we employ a 3D morphable face model [2,3]. The model's database contains m = 512 faces ranging from the age of 3 months to ⇡ 40 years with an approximately equal number of female and male individuals (200 adults, 236 children aged between 7 and 16 years and 76 very young children aged between 3 and 12 months).…”

“…The algorithm robustly detects faces despite apparent variation of facial attributes such as increased body weight, beards, bright or dark skin color. a few randomized facial samples which we gain from a 3D morphable face model [2,3]. Each 3D random face is then modulated by automatically changing a set of facial attributes such as gender, weight or age.…”