Real Time Facial Emotions Detection Using Convolutional Neural Network

Abstract

Facial emotions or expressions are recognized by computers and enhancing modern-day machines to understand human emotions from their reality time. Through this project, i'd wish to provide solution for real face expressions or emotions by video capture from emotion detector frame by Open-CV it'll capture video by camera which is built-in to the machine or ADPS. The countenance are identified by different operations provided by OpenCV and also the region consisting of parts of the face are made to surround or enclose by a contour. This region, enclosed by the contour is used as an input to the Convolutional Neural Network (CNN). The CNN model created consists of six activation layers, of which four are convolution layers and two are fully controlled layers. The scope of the project is to demonstrate the accuracy and validation of Convolution Neural Network (CNN).