Single View Facial Age Estimation Using Deep Learning with Cascaded Random Forests
Single View Facial Age Estimation Using Deep Learning with Cascaded Random Forests
复制标题
DOI：
10.1007/978-3-030-89131-2_26
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Imad Eddine Toubal;Linquan Lyu;D. Lin;K. Palaniappan
中科院分区：
文献类型：
--
作者：
Imad Eddine Toubal;Linquan Lyu;D. Lin;K. Palaniappan
使用无约束的面部图像来估计人的真实的年龄的任务已经在生物测定研究中被积极地研究。我们开发了几种用于面部年龄估计的深度学习架构和监督方法，并评估了不同预处理和面部对齐（或归一化）方法对特征嵌入子空间的影响。提出的新的两阶段监督学习模型利用ResNeXt作为骨干，结合双层随机森林（TLRF）来估计年龄。我们的深度架构使用自定义损失函数进行训练，以处理性别，姿势，照明，种族，表情和上下文的变化，VGG-Face 2 MIVIA年龄数据集拥有超过575 K的图像，作为猜测年龄（GTA）比赛的一部分。令人惊讶的是，在训练过程中使用FANet进行面部对齐并没有提高准确性。我们能够实现一个年龄准确性和规律性得分与方差只使用ResNeXt。所提出的ResNeXt+TLRF模型提高了年龄级的泛化能力，具有较小的方差和次优。
The task of estimating a person’s real age using unconstrained facial images has been actively studied in biometrics research. We developed several deep learning architectures and supervision methods for facial age estimation and evaluate the impact of different pre-processing and face alignment (or normalization) methods on the feature embedding subspace. The proposed novel two-stage supervised learning model utilizes ResNeXt as a backbone combined with a two-layer random forest (TLRF) to estimate age. Our deep architectures are trained using a custom loss function to handle variations in gender, pose, illumination, ethnicity, expression and context, on theVGG-Face2 MIVIA Age Datasetwith over 575K images, as part of the Guess the Age (GTA) contest. Surprisingly, face alignment using FANet during training did not improve accuracy. We were able to achieve an Age Accuracy and Regularity scorewith a varianceusing only ResNeXt. The proposed ResNeXt+TLRF model improved age-class generalizability with a smaller variance ofand a second best.