Toward Automatic Simulation of Aging Effects on Face Images

By Andreas Lanitis, Christopher J. Taylor, Tim Cootes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002

960 citations recorded by the source corpus.

The process of aging causes significant alterations in the facial appearance of individuals. When compared with other sources of variation in face images, appearance variation due to aging displays some unique characteristics. Changes in facial appearance due to aging can even affect discriminatory facial features, resulting in deterioration of the ability of humans and machines to identify aged individuals. We describe how the effects of aging on facial appearance can be explained using learned age transformations and present experimental results to show that reasonably accurate estimates of age can be made for unseen images. We also show that we can improve our results by taking into account the fact that different individuals age in different ways and by considering the effect of lifestyle. Our proposed framework can be used for simulating aging effects on new face images in order to predict how an individual might look like in the future or how he/she used to look in the past. The methodology presented has also been used for designing a face recognition system, robust to aging variation. In this context, the perceived age of the subjects in the training and test images is normalized before the training and classification procedure so that aging variation is eliminated. Experimental results demonstrate that, when age normalization is used, the performance of our face recognition system can be improved.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ca5b01a31a8653cc048344b0806c756fb53e9cde

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

Citations in the corpus

Modeling Age Progression in Young Faces (2006, methodology): “Further, Lanitis et al. [12] compared the above age estimation process with that of neural networks based approaches.”
Age-Invariant Face Recognition (2010, methodology): “This result shows that the forehead does influence the face recognition performance, although it has been a common practice to remove the forehead in AAM-based feature point detection and subsequent face modeling [4], [6], [18].”
Facial Age Estimation by Learning from Label Distributions (2010, methodology): “One of the early works on exact age estimation was done by Lanitis et al. [20], [19], where the aging pattern was represented by a quadratic function called aging function .”
Human Age Estimation With Regression on Discriminative Aging Manifold (2008, methodology): “These overall results are consistent with the reports from [11], [12].”
Age Synthesis and Estimation via Faces: A Survey (2010, methodology): “[17] also tried different classifiers for age estimation based on their age image representation, especially the quadratic aging function [122].”
Modifying the Memorability of Face Photographs (2013, methodology): “This might suggest why, unlike our method, existing methods [17, 18] typically use landmark-based features instead of dense global features for the modification of facial attributes.”
What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics (2016, background): “Interesting work can be found in [144] (Lanitis et al.”
Demographic Estimation from Face Images: Human vs. Machine Performance (2015, background): “Since then, a significant progress has been made on automatic demographic estimation, and a number of approaches have been reported in the literature [8], [17], [19], [21], [23], [27], [29], [33], [39], [44], [51], [54].”
Learning from facial aging patterns for automatic age estimation (2006, methodology): “in [13], WAS is the best one without using the ‘lifestyle profiles’, and among the methods proposed in [12], AAS achieved the best performance.”
Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval (2014, methodology): “Most existing age-related works for face image analysis focus on age estimation [14,15,40,25,34,7,38,6,10,22,21] and age simulation [16,30,28,29,24].”
Face Recognition and Retrieval Using Cross-Age Reference Coding With Cross-Age Celebrity Dataset (2015, methodology): “One of the approaches is to construct 2D or 3D aging models [23], [24], [22] to reduce the age variation in face matching.”
Longitudinal Study of Automatic Face Recognition (2018, background): “and age-invariant face recognition, are FG-NET [15] and MORPH [16].”
2D and 3D face recognition: A survey (2007, methodology): “In a recent work Lanitis and Taylor (2000) and Lanitis et al. (2002) proposed a new method based on age functions.”
Comparing different classifiers for automatic age estimation (2004, background): “A description of our early work in this area is described elsewhere [15].”
Face verification across age progression (2005, background): “Lanitis et al. [24] proposed methods to simulate aging effects on face images.”