FG2015 age progression evaluation
FG2015 age progression evaluation
复制标题
DOI：
10.1109/fg.2015.7163157
复制
发表时间：
2015-05
期刊：
影响因子：
--
通讯作者：
A. Lanitis;N. Tsapatsoulis;Kleanthis Soteriou;Daiki Kuwahara;S. Morishima
中科院分区：
文献类型：
--
作者：
A. Lanitis;N. Tsapatsoulis;Kleanthis Soteriou;Daiki Kuwahara;S. Morishima
近年来，人脸老化问题越来越受到计算机视觉界的关注。这种兴趣是由可以使用精确年龄进展算法的重要现实生活应用所激发的。然而，年龄递进方法只能在实际应用中使用，前提是它们能够产生准确的年龄递进图像。因此，通过制定性能评估协议来鼓励准确年龄进展算法的发展是至关重要的，这些协议可用于对文献中报道的不同算法获得准确的性能评估结果。在本文中，我们描述的组织，有史以来第一次，试点独立的年龄进展竞赛，旨在提供一个稳健的框架评估年龄进展方法的基础。所进行的评估涉及使用几种基于机器和基于人的指标，用于评估八种年龄进展方法。
The topic of face-aging received increased attention by the computer vision community during the recent years. This interest is motivated by important real life applications where accurate age progression algorithms can be used. However, age progression methodologies may only be used in real applications provided that they have the ability to produce accurate age progressed images. Therefore it is of utmost importance to encourage the development of accurate age progression algorithms through the formulation of performance evaluation protocols that can be used for obtaining accurate performance evaluation results for different algorithms reported in the literature. In this paper we describe the organization of the, first ever, pilot independent age progression competition that aims to provide the basis of a robust framework for assessing age progression methodologies. The evaluation carried out involves the use of several machine-based and human-based indicators that were used for assessing eight age progression methods.