Facial Expression Recognition in Videos: An CNN-LSTM based Model for Video Classification
Muhammad Abdullah, Mobeen Ahmad, Dongil Han
20202020 International Conference on Electronics, Information, and Communication (ICEIC)45 citationsDOI
Abstract
Facial Expressions are an integral part of human communication. Therefore, correct classification of facial expression in image and video data has been an important quest for researchers and software development industry. In this paper we propose the video classification method using Recurrent Neural Networks (RNN) in addition to Convolution Neural Networks (CNN) to capture temporal as well spatial features of a video sequence. The methodology is tested on The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). Since no other results were available on this dataset using only visual analysis, the proposed method provides the first benchmark of 61% test accuracy on given dataset.
Topics & Concepts
Computer scienceBenchmark (surveying)Convolutional neural networkArtificial intelligenceFacial expressionConvolution (computer science)Speech recognitionRecurrent neural networkExpression (computer science)Pattern recognition (psychology)SoftwareDeep learningArtificial neural networkGeographyProgramming languageGeodesyHuman Pose and Action RecognitionVideo Surveillance and Tracking MethodsVideo Analysis and Summarization