A Compositional and Dynamic Model for Face Aging

A Compositional and Dynamic Model for Face Aging
复制标题

面部老化的组成和动态模型

DOI:
10.1109/tpami.2009.39
复制
发表时间:
2010-03
影响因子:
23.6
通讯作者:
--
中科院分区:
计算机科学1区
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

在本文中,我们提出了一个人脸老化的组成和动态模型。组合模型通过分层的And- Or图表示每个年龄组的面部,其中And节点将面部分解成部分来描述对年龄感知至关重要的细节(例如,头发,皱纹等),Or节点通过替代选择表示大量的面部多样性。那么一个face实例就是And-or图解析图的横向。将人脸老化建模为基于解析图表示的马尔可夫过程。我们从大量带注释的人脸数据集中学习动态模型的参数,并在动态模型中明确地建模了人脸老化的随机性。基于该模型,提出了一种人脸老化仿真与预测算法。在此基础上,提出了一种年龄自动估计算法。我们研究了人类感知实验衰老结果的两个评价标准:(1)模拟的准确性:衰老的面孔是否被认为是预期的年龄组;(2)身份的保留:衰老的面孔是否被认为是同一个人。定量统计分析验证了我们的老化模型和年龄估计算法的性能。
In this paper, we present a compositional and dynamic model for face aging. The compositional model represents faces in each age group by a hierarchical And-or graph, in which And nodes decompose a face into parts to describe details (e.g., hair, wrinkles, etc.) crucial for age perception and Or nodes represent large diversity of faces by alternative selections. Then a face instance is a transverse of the And-or graph-parse graph. Face aging is modeled as a Markov process on the parse graph representation. We learn the parameters of the dynamic model from a large annotated face data set and the stochasticity of face aging is modeled in the dynamics explicitly. Based on this model, we propose a face aging simulation and prediction algorithm. Inversely, an automatic age estimation algorithm is also developed under this representation. We study two criteria to evaluate the aging results using human perception experiments: (1) the accuracy of simulation: whether the aged faces are perceived of the intended age group, and (2) preservation of identity: whether the aged faces are perceived as the same person. Quantitative statistical analysis validates the performance of our aging model and age estimation algorithm.
DOI: 10.2307/j.ctv15r57jg
发表时间: 1967-02
期刊: --
影响因子: --
作者:
Edward Nelson
通讯作者: Edward Nelson
DOI: 10.1109/tcsvt.2006.877398
发表时间: 2006-07
影响因子: 8.4
作者:
Yun Fu;Nanning Zheng
通讯作者: Yun Fu;Nanning Zheng
DOI: 10.1109/iv.2006.8
发表时间: 2006-07
期刊: Tenth International Conference on Information Visualisation (IV'06)
影响因子: --
作者:
Alexandre Cruz Berg;Francisco J. Perales López;Manuel González Hidalgo
通讯作者: Alexandre Cruz Berg;Francisco J. Perales López;Manuel González Hidalgo
DOI: 10.1006/cviu.1997.0549
发表时间: 1999-04-01
影响因子: 4.5
作者:
Kwon, YH;Lobo, ND
通讯作者: Lobo, ND
DOI: 10.1109/afgr.2008.4813337
发表时间: 2008-09
期刊: 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition
影响因子: --
作者:
Narayanan Ramanathan;R. Chellappa
通讯作者: Narayanan Ramanathan;R. Chellappa