基于神经网络的面部表情鉴别系统的研究与实现

北京理工大学珠海学院2020届本科生毕业论文Facial expression identification systembased on Neural NetworkAbstractWith the development of the era of artificial intelligence,the people-oriented researchconcept has become the main research direction.In order to allow computers to understandhuman wishes and inner needs,facial expression identification has become a key technologyfor computers to understand changes in human emotions.It distinguishes facial expressionsby extracting and classifying features of facial expressions.So far,the application value of thistechnology can be reflected in many industries such as human-computer interaction,onlineeducation and safe driving.There are many research methods for facial expressionidentification,and this paper mainly studies the facial expression identification system basedon neural network.In this paper,the Fer2013 data set is selected as the data set for this model training andpre-processed to obtain a data set of six expressions.Then,an 11-layer network structuremodel based on the principle of convolutional neural network is designed,including 4convolutional layers,3 pooling layers and 4 fully connected layers,and the training results areanalyzed.According to the final test,the model's facial expression discrimination accuracy is62%.The camera will be used to collect face images in real time and identify them,and theidentification effect for Normal and happy is better,followed by the identification of theremaining expressions.In view of the above results,this paper puts forward the feasibility and shortcomings ofthe program.Keywords:Facial expression identification,convolutional neural network,Data setpreprocessing,Tensorflow framework