Facial Expression Detector Using a Five-Layered Convolutional Neural Networks 
Queenie Das1, Geetika Gopi2, Janani Suresh3, Swarnalatha P4
1Queenie Das*, Research scholar Department of Computer Science and Engineering (SCOPE), Vellore Institute of Technology, Vellore, Tamil Nadu, India.
2Geetika Gopi, Research scholar Department of Computer Science and Engineering (SCOPE), Vellore Institute of Technology, Vellore, Tamil Nadu, India.
3Janani Suresh, Research scholar Department of Computer Science and Engineering (SCOPE), Vellore Institute of Technology, Vellore, Tamil Nadu, India.
4Swarnalatha P, Associate Professor, Department of Computer Science and Engineering (SCOPE), Vellore Institute of Technology, Vellore, Tamil Nadu, India.
Manuscript received on November 12, 2019. | Revised Manuscript received on November 25, 2019. | Manuscript published on 30 November, 2019. | PP: 4526-4530 | Volume-8 Issue-4, November 2019. | Retrieval Number: D8457118419/2019©BEIESP | DOI: 10.35940/ijrte.D8457.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: A face is a very important aspect in communication. Often, it is through face expressions that people understand what another person is trying to convey or in what mood he/she is saying it in. It also helps in realising what a person’s mental or emotional state is at a particular moment of time.Thus, recognising a facial expression is essential in day to day communication. Our proposed model implements a facial expression recogniser that categorises a face expression into one of the seven expressions: Happy, Sad, Angry, Surprised, Fearful, Neutral andDisgusted. The model uses Convolutional Neural Network (CNN) having five layers. The model gives an immediate representation ofthe predicted expression by displaying an emoji associated with. Not just that, our model will also show the percentage of each of the seven expressions so that the understanding of the expression is better.A face expression recogniser can be used in areas face biometrics, forensics and security system. Not only that, it can be used in a commercial or financial aspect by judging customer interests. Also, ararely used application of such an application is to aid Autistic people in communication.
Keywords: Convolution neural network, Emoticons, Facial Expression, Machine Learning.
Scope of the Article: Machine Learning.