用于人脸表情识别的多分辨率特征融合卷积神经网络  

Convolution Neural Network with Multi-Resolution Feature Fusion for Facial Expression Recognition

作　　者：何志超 赵龙章 陈闯 He Zhichao;Zhao Longzhang;Chen Chuang(College of Electrical Engineering and Control Science,Nanjing Tech University,Nanjing,Jiangsu 211816,China)

机构地区：[1]南京工业大学电气工程与控制科学学院,江苏南京211816

出　　处：《激光与光电子学进展》2018年第7期364-369,共6页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(51277028)

摘　　要：在人脸表情识别任务中,传统的机器学习方法是基于人工来提取特征,其特征提取过程时间复杂度高且稳健性差,而现有依赖单通道卷积核的卷积神经网络提取特征不够充分,进而导致识别率不高。针对这些问题,提出一种多分辨率特征融合的卷积神经网络。利用两个相互独立且深度不同的通道对图片进行特征提取,使卷积神经网络自主学习同一图像下不同分辨率的特征,然后将不同分辨率的特征送入全连接层并进行特征融合,最后经过softmax分类器进行表情分类。在JAFFE和CK+表情数据库上进行了多次实验,结果表明,与传统的机器学习方法和现有的卷积神经网络结构相比,所提卷积神经网络结构模型具有稳健性好、泛化能力强、收敛速度快的优点。In facial expression recognition,the traditional machine learning methods based on the manual feature extraction are time-consuming and less robust.The current convolution neural networks relying on single channel convolution kernel are not sufficient to extract feature,which makes the recognition rates low.We propose a multiresolution feature fusion convolution neural network,which is combined with two uncorrelated and channels with different depths to extract multi-resolution features.After fusing the two channels feature,a softmax classification is used to classify the facial expression.The experiments on JAFFE and CK＋facial expression databases show that compared with traditional machine learning methods and existing convolution neural networks,the proposed convolution neural network structure model has the advantages of good robustness,strong generalization ability,and fast convergence speed.

关 键 词：机器视觉 人脸表情识别 特征提取 卷积神经网络 多分辨率特征融合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]