arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.10892cs.CV
收藏

基于深度和手工特征的局部学习人脸表情识别

Local Learning with Deep and Handcrafted Features for Facial Expression Recognition

University of Bucharest(布加勒斯特大学);Novustech Services;SecurifAI

Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Marius Popescu

摘要:

我们提出了一种方法,该方法结合了卷积神经网络(CNN)学习的自动特征和视觉词袋(BOVW)模型计算的手工特征,以实现面部表情识别的最新结果。为了获得自动特征,我们使用多个CNN架构、预训练模型和训练过程进行实验,例如密集-稀疏-密集。在融合两种类型的特征之后,我们采用局部学习框架来预测每个测试图像的类别标签。地方学习框架基于三个步骤。首先,应用k-最近邻模型,以便为输入测试图像选择最近的训练样本。其次,一个一对所有的支持向量机(SVM)分类器的训练上选择的训练样本。最后,SVM分类器被用来预测类标签只为测试图像,它是训练。虽然我们在以前的工作中结合手工特征使用了局部学习,但据我们所知,局部学习从未与深度特征结合使用。在2013年人脸表情识别(FER)挑战赛数据集、FER+数据集和AffectNet数据集上的实验表明,我们的方法达到了最先进的结果。FER 2013的最高准确率为75.42%,FER+为87.76%,AffectNet 8路分类为59.58%,AffectNet 7路分类为63.31%,我们在所有数据集上都超过了最先进的方法1%以上。

英文摘要:

We present an approach that combines automatic features learned by convolutional neural networks (CNN) and handcrafted features computed by the bag-of-visual-words (BOVW) model in order to achieve state-of-the-art results in facial expression recognition. To obtain automatic features, we experiment with multiple CNN architectures, pre-trained models and training procedures, e.g. Dense-Sparse-Dense. After fusing the two types of features, we employ a local learning framework to predict the class label for each test image. The local learning framework is based on three steps. First, a k-nearest neighbors model is applied in order to select the nearest training samples for an input test image. Second, a one-versus-all Support Vector Machines (SVM) classifier is trained on the selected training samples. Finally, the SVM classifier is used to predict the class label only for the test image it was trained for. Although we have used local learning in combination with handcrafted features in our previous work, to the best of our knowledge, local learning has never been employed in combination with deep features. The experiments on the 2013 Facial Expression Recognition (FER) Challenge data set, the FER+ data set and the AffectNet data set demonstrate that our approach achieves state-of-the-art results. With a top accuracy of 75.42% on FER 2013, 87.76% on the FER+, 59.58% on AffectNet 8-way classification and 63.31% on AffectNet 7-way classification, we surpass the state-of-the-art methods by more than 1% on all data sets.

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。

↑