Machine-learning-based age estimation has received lots of attention. Traditional age estimation mechanism focuses estimation age error, but ignores that there is a deviation between the estimated age and real age due to disease. Pathological age estimation mechanism the author proposed before introduces age deviation to solve the above problem and improves classification capability of the estimated age significantly. However,it does not consider the age estimation error of the normal control (NC) group and results in a larger error between the estimated age and real age of NC group. Therefore, an integrated age estimation mechanism based on Decision-Level fusion of error and deviation orientation model is proposed to solve the problem.Firstly, the traditional age estimation and pathological age estimation mechanisms are weighted together.Secondly, their optimal weights are obtained by minimizing mean absolute error (MAE) between the estimated age and real age of normal people. In the experimental section, several representative age-related datasets are used for verification of the proposed method. The results show that the proposed age estimation mechanism achieves a good tradeoff effect of age estimation. It not only improves the classification ability of the estimated age, but also reduces the age estimation error of the NC group. In general, the proposed age estimation mechanism is effective. Additionally, the mechanism is a framework mechanism that can be used to construct different specific age estimation algorithms, contributing to relevant research.
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Baidu Research(百度研究院);National Engineering Laboratory for Deep Learning Technology and Application(深度学习技术及应用国家工程实验室);Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences(中国科学院香港创新研究院人工智能与机器人创新中心)
人脸年龄估计是计算机视觉中一个重要而又极具挑战性的问题。为了提高人脸年龄估计的性能,本文首先建立了一个简单的标准基线,然后通过收集预训练、数据增强、模型构建等技巧,建立了一个更强的基线,与标准基线相比,该基线显著降低了估计误差。此外,长尾识别一直是面部年龄数据集中的一个重要课题,其中老年人和儿童的样本往往缺乏。为了训练均衡年龄估计器,提出了一种两阶段的训练方法--长尾年龄估计(Long-tailed Age Estimation,LAE),将学习过程分为表示学习和分类两个阶段。我们的方法的有效性已在Guess The Age Contest 2021的组织者提供的数据集上得到证明。
Fine-Grained Age Estimation in the wild with Attention LSTM Networks
North China Electric Power University(华北电力大学);University of Missouri(密苏里大学)
基于单幅人脸图像的年龄估计是人机交互和计算机视觉领域的一个重要研究课题,具有广泛的实际应用价值。现有的人脸图像年龄估计方法只考虑了全局特征,而忽略了年龄敏感区域的细粒度特征,因此在野外人脸图像年龄估计中精度较低。受细粒度分类和视觉注意力机制的启发,我们提出了一种基于我们的注意力长短期记忆(AL)网络的细粒度年龄估计方法。该方法将残差网络(ResNets)或残差网络模型的残差网络(RoR)与LSTM单元相结合,构建AL-ResNets或AL-RoR网络,提取年龄敏感区域的局部特征,有效提高了年龄估计精度。首先,选择在ImageNet数据集上预训练的ResNets或RoR模型作为基本模型,然后在IMDB-WIKI-101数据集上进行微调以进行年龄估计。然后,我们在目标年龄数据集上微调ResNets或RoR,以提取人脸图像的全局特征。为了提取年龄敏感区域的局部特征,然后提出LSTM单元来自动获得年龄敏感区域的坐标。最后,直接在Adience数据集上进行年龄组分类,并在MORPH Album 2,FG-NET和15/16 m2数据集上使用Deep Expectation算法(DEX)进行年龄回归实验。通过结合全局和局部特征,我们得到我们最终的预测结果。实验结果表明,所提出的AL-ResNets或AL-RoR的有效性和鲁棒性的年龄估计在野外,其中它实现了更好的最先进的性能比所有其他卷积神经网…
National Laboratory of Pattern Recognition, CASIA(中国科学院自动化研究所模式识别国家重点实验室);Center for Research on Intelligent Perception and Computing, CASIA(中国科学院自动化研究所智能感知与计算研究中心);University of Chinese Academy of Sciences(中国科学院大学)
Assessing the Influencing Factors on the Accuracy of Underage Facial Age Estimation
University College Dublin(都柏林大学学院)
对发现濒危未成年人的迅速反应是执法部门持续关注的问题。许多以儿童为中心的调查取决于数字证据的发现和分析。需要自动年龄估计技术来帮助这些调查,以加快证据发现过程,并减少调查人员接触创伤材料。自动化技术也显示出减少从越来越多的设备和在线服务中获得的证据积压的希望。长期以来,缺乏足够的训练数据加上自然的人类差异一直阻碍着准确的自动年龄估计-特别是对于未成年人。本文对两种云年龄估计服务(Amazon Web Service的Rekognition服务和Microsoft Azure的Face API)的性能进行了全面评估,针对超过21,800名未成年受试者的数据集。这项工作的目的是评估某些人类生物特征因素,面部表情和图像质量(即模糊,噪声,曝光和分辨率)对自动年龄估计服务结果的影响。一个彻底的评估,使我们能够确定最有影响力的因素,以克服在未来的年龄估计系统。