In this paper, we propose a multi-task representation learning framework to jointly estimate the identity, gender and age of individuals from their hand images for the purpose of criminal investigations since the hand images are often the only available information in cases of serious crime such as sexual abuse. We investigate different up-to-date deep learning architectures and compare their performance for joint estimation of identity, gender and age from hand images of perpetrators of serious crime. To overcome the data imbalance and simplify the age prediction, we create age groups for the age estimation. We make extensive evaluations and comparisons of both convolution-based and transformer-based deep learning architectures on a publicly available 11k hands dataset. Our experimental analysis shows that it is possible to efficiently estimate not only identity but also other attributes such as gender and age of suspects jointly from hand images for criminal investigations, which is crucial in assisting international police forces in the court to identify and convict abusers.

翻译：本文提出一种多任务表示学习框架，旨在通过犯罪嫌疑人的手部图像联合估计其身份、性别与年龄。由于在性侵等严重犯罪案件中，手部图像往往是唯一可获取的信息来源，该研究可为刑事调查提供关键支撑。我们研究了多种前沿深度学习架构，并比较了它们在严重犯罪 perpetrators 手部图像联合身份、性别与年龄估计任务中的表现。为克服数据不平衡问题并简化年龄预测，我们构建了年龄分组进行年龄估计。基于公开的11k Hands数据集，我们系统评估并比较了卷积神经网络与Transformer两类深度学习架构的性能。实验结果表明，通过手部图像联合估计嫌疑人的身份、性别与年龄属性是可行的，这将在法庭审判中为国际刑警组织识别并定罪施暴者提供关键技术支持。