Discriminative Deep Feature Learning for Facial Emotion Recognition
Discriminative Deep Feature Learning for Facial Emotion Recognition
复制标题
用于面部情绪识别的判别式深度特征学习
DOI：
10.1109/mapr.2018.8337514
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Pham Thai Ha
中科院分区：
文献类型：
--
作者：
D. V. Sang;Le Tran Bao Cuong;Pham Thai Ha
情感识别是人脸表情分析中的一项重要任务，具有广泛的应用前景。这项任务的目标是将面部图像分为七类：厌恶，中性，悲伤，快乐，恐惧，惊讶和愤怒。在本文中，我们提出了一种基于密集卷积网络（DenseNet）的区分性深度特征学习方法，用于面部情感识别。特别地，我们采用辅助损失，即中心损失，来调节神经网络的训练过程，以减少深层特征的类内变化，从而提高学习网络的区分能力。实验结果表明，我们提出的方法实现了上级性能相比，其他最近的国家的最先进的方法在著名的FERC-2013数据集。
Emotion recognition is an important task in facial expression analysis with various potential applications. The goal of this task is to classify facial images into seven classes: disgust, neutral, sad, happy, fear, surprise and angry. In this paper, we propose a discriminative deep feature learning approach with dense convolutional networks (DenseNet) for facial emotion recognition. Particularly, we employ an auxiliary loss, namely center loss, to regulate the training process of neural networks in order to reduce the intra-class variation of the deep features and, hence, to enhance the discriminative power of the learned networks. The experimental results show that our proposed approach achieves superior performance in comparison with other recent state- of-the-art methods on the well-known FERC-2013 dataset.