arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09982cs.CVcs.AIcs.LG
收藏

应用于面部表情识别的数据增强与迁移学习方法

Data Augmentation and Transfer Learning Approaches Applied to Facial Expressions Recognition

QuestIT Research Lab(QuestIT研究实验室)

Enrico Randellini, Leonardo Rigutini, Claudio Sacca'

AI总结:

针对训练数据集规模小的问题,提出结合几何变换与GAN生成图像的数据增强技术,并在增强数据集上微调预训练卷积神经网络,使InceptionResNetV2模型在跨库测试中达到约85%的平均准确率。

摘要:

面部表情是我们想了解一个人心理状态时首先关注的事物。因此,以自动方式识别面部表情的能力是一个非常有趣的研究领域。在本文中,由于可用训练数据集规模较小,我们提出了一种新颖的数据增强技术,以提高识别任务的性能。我们应用几何变换,并从头开始构建能够为每种情绪类型生成新合成图像的GAN模型。随后,在增强后的数据集上,我们对具有不同架构的预训练卷积神经网络进行微调。为了衡量模型的泛化能力,我们采用跨库协议方法,即在训练数据集的增强版本上训练模型,并在两个不同的数据库上进行测试。这些技术的结合使得InceptionResNetV2模型能够达到约85%的平均准确率。

英文摘要:

The face expression is the first thing we pay attention to when we want to understand a person's state of mind. Thus, the ability to recognize facial expressions in an automatic way is a very interesting research field. In this paper, because the small size of available training datasets, we propose a novel data augmentation technique that improves the performances in the recognition task. We apply geometrical transformations and build from scratch GAN models able to generate new synthetic images for each emotion type. Thus, on the augmented datasets we fine tune pretrained convolutional neural networks with different architectures. To measure the generalization ability of the models, we apply extra-database protocol approach, namely we train models on the augmented versions of training dataset and test them on two different databases. The combination of these techniques allows to reach average accuracy values of the order of 85\% for the InceptionResNetV2 model.

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。

↑