Nowadays we have seen that the study of facial expression recognition became most important. In humans, the way of interaction will possible through text and voice. Apart from that, facial expressions play an important role in smooth communication among individuals. We can recognize the emotion of a human, based on facial expressions. First of all, facial areas were removed from the original images. Meanwhile, by using the different types of optimizers we have trained the convolutional neural network mainly focused on the face extraction. The accuracy of other methods like 2D PCA is 78.61%, Adaboost is 83.12%, SVM is 87.15%. In this paper, the method we proposed is softmax classifier by which we obtained an accuracy of 94.82% which is the highest among all. Here this softmax classifier we have used in this experiment, suggests the combination of face detection and emotion detection using CNN.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.