A Multi-Resolution Dynamic Model for Face Aging Simulation

Suo, Jinli; Min, Feng; Zhu, Song‐Chun; Shan, Shiguang; Chen, Xilin

doi:10.1109/cvpr.2007.383055

Cited by 97 publications

(78 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Tiddeman et al [11] used wavelet-based methods for prototyping and transforming the facial textures to identify salient features such as age wrinkles in prototype facial images, and apply them to other images to change the apparent age. Suo et al [9] presented a model for simulating aging process with two dimensional facial images. The model integrates three aspects related to aging changes: global appearance changes in hair style and shape, deformations and aging effects of facial components, and wrinkle appearance at various facial zones.…”

Section: Related Workmentioning

confidence: 99%

Growth Simulation of Facial/Head Model from Childhood to Adulthood

Lin¹,

Lai²,

Cheng³

2010

Computer-Aided Design and Applications

View full text Add to dashboard Cite

This paper presents a method to simulate the growth of the facial/head model of a person from childhood to adulthood. The method works by generating continuous data of standard landmarks using auto-regressive moving average based on anthropometry of the head/face. The standard landmarks are assigned to the particular head and face, and vertices of the growing head/facial model are calculated by projecting the vertices to the one dimensional subspace that contains measurements of the landmarks. The vertices of the predicted model are constrained to keep the features of the head/face distinct by grouping vertices into clusters and maintaining each cluster proportionally changing in different age periods. This new technology has applications in security, ID search (for missing children), health care (such as, evaluation of dysmorphic children) and forensic sketch artistry.

show abstract

Section: Related Workmentioning

confidence: 99%

Growth Simulation of Facial/Head Model from Childhood to Adulthood

Lin¹,

Lai²,

Cheng³

2010

Computer-Aided Design and Applications

View full text Add to dashboard Cite

show abstract

“…With 2D projection, growth parameters for landmarks can only be estimated based on a limited number of facial proportions that can be reliably estimated from photogrammetry of frontal images. The proposed 3D model would allow us to incorporate texture into individual facial components such as eye, mouth, and forehead, which is in line with the aging simulation method based on a graph structure [22]. 3D models can also be used to locate muscle fibers, and wrinkles can be generated across and orthogonal to the fibers [9].…”

Section: Aging Modelmentioning

confidence: 99%

“…A few image-based approaches in 2D have already been proposed to simulate both growth and adult aging, e.g. [20,22]. These seminal studies demonstrated the feasibility of improving face recognition accuracy by simulated aging.…”

Section: Related Workmentioning

confidence: 99%

Face recognition with temporal invariance: A 3D aging model

Park

Tong

Jain

2008

2008 8th IEEE International Conference on Automatic Face &Amp; Gesture Recognition

View full text Add to dashboard Cite

“…One recent work bearing some similarity with ours is [38], in which a dynamic face aging model based on a hierarchical face representation is proposed. However, the dynamics in [38] are learned from predefined similarity metrics instead of real aging data and the continuous aging process is simplified by dividing age range into 5 discrete groups.…”

Section: Motivation and Basic Ideasmentioning

confidence: 99%