arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.02481cs.CV
收藏

MAFER:一种多分辨率人脸表情识别方法

MAFER: a Multi-resolution Approach to Facial Expression Recognition

Istituto di Scienza e Tecnologie dell’Informazione “Alessandro Faedo” – CNR(意大利国家研究委员会信息科学与技术研究所“亚历山德罗·法埃多”)

Fabio Valerio Massoli, Donato Cafarelli, Claudio Gennaro, Giuseppe Amato, Fabrizio Falchi

摘要:

情绪在每个人的社会生活中起着核心作用,对情绪的研究是一个多学科的课题,涵盖了各种各样的研究领域。特别是关于后者,面部表情的分析代表了一个非常活跃的研究领域,由于其相关的人机交互应用。在这样的背景下,面部表情识别(FER)是识别人脸上的表情的任务。通常,面部图像由本质上具有不同特性(诸如输出分辨率)的相机获取。文献中已经表明,应用于人脸识别的深度学习模型在针对多分辨率场景进行测试时,其性能会下降。由于FER任务涉及分析可以用异构源获取的面部图像,因此涉及具有不同质量的图像,因此可以合理地预期分辨率在这种情况下也起着重要作用。从这样一个假设出发,我们证明了多分辨率训练对识别面部表情的模型的好处。因此,我们提出了一个两步学习过程,名为MAFER,训练DCNN,使他们能够在广泛的分辨率生成强大的预测。MAFER的一个相关特征是它是任务不可知的,即,它可以补充地用于其他与目标相关的技术。为了评估所提出的方法的有效性,我们进行了广泛的实验活动公开可用的数据集:\fer{},\raf{},和\oulu{}。对于多分辨率环境,我们观察到,使用我们的方法,学习模型改进了当前的SotA,同时在固定分辨率环境中报告了可比的结果。最后,我们分析了我们的模型的性能,并观察到从它们生成的深层特征的更高的辨别力。

英文摘要:

Emotions play a central role in the social life of every human being, and their study, which represents a multidisciplinary subject, embraces a great variety of research fields. Especially concerning the latter, the analysis of facial expressions represents a very active research area due to its relevance to human-computer interaction applications. In such a context, Facial Expression Recognition (FER) is the task of recognizing expressions on human faces. Typically, face images are acquired by cameras that have, by nature, different characteristics, such as the output resolution. It has been already shown in the literature that Deep Learning models applied to face recognition experience a degradation in their performance when tested against multi-resolution scenarios. Since the FER task involves analyzing face images that can be acquired with heterogeneous sources, thus involving images with different quality, it is plausible to expect that resolution plays an important role in such a case too. Stemming from such a hypothesis, we prove the benefits of multi-resolution training for models tasked with recognizing facial expressions. Hence, we propose a two-step learning procedure, named MAFER, to train DCNNs to empower them to generate robust predictions across a wide range of resolutions. A relevant feature of MAFER is that it is task-agnostic, i.e., it can be used complementarily to other objective-related techniques. To assess the effectiveness of the proposed approach, we performed an extensive experimental campaign on publicly available datasets: \fer{}, \raf{}, and \oulu{}. For a multi-resolution context, we observe that with our approach, learning models improve upon the current SotA while reporting comparable results in fix-resolution contexts. Finally, we analyze the performance of our models and observe the higher discrimination power of deep features generated from them.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑