摘要
为了避免传统的表情识别中复杂的显式特征提取过程,文中提出了一种用于人脸表情识别的卷积神经网络(CNN)。首先,对人脸表情图像进行归一化预处理,并使用可训练的卷积核提取隐式的特征。然后,采用最大池化方法对提取的隐式特征进行降维处理。最后,采用Softmax分类器对测试样本图像的表情进行分类识别。使用图形处理器(GPU)在CK+人脸表情数据库上进行了实验,结果表明了CNN用于人脸表情识别的性能和泛化能力。
To avoid the complex explicit feature extraction process in traditional expression recognition,a convolutional neural network( CNN) for the facial expression recognition is proposed. Firstly,the facial expression image is normalized and the implicit features are extracted by using the trainable convolution kernel. Then,the maximum pooling is used to reduce the dimensions of the extracted implicit features. Finally,the Softmax classifier is used to classify the facial expressions of the test samples. The experiment is carried out on the CK + facial expression database using the graphics processing unit( GPU). Experimental results show the performance and the generalization ability of the CNN for facial expression recognition.
出处
《南京邮电大学学报(自然科学版)》
北大核心
2016年第1期16-22,共7页
Journal of Nanjing University of Posts and Telecommunications:Natural Science Edition
基金
国家自然科学基金(61071167
61501249)
江苏省高校优秀中青年教师和校长境外研修计划
江苏省高校自然科学研究(15KJB510022)
江苏省普通高校研究生实践创新计划(SJLX15_0371)资助项目
关键词
人脸表情识别
卷积神经网络
深度学习
图形处理器
特征提取
facial expression recognition
convolutional neural networks
deep learning
graphics processing unit
feature extraction