Publication

Abstract : The recognition of facial emotions has received growing focus in recent years due to its importance and the significant role it plays in shaping the way humans interact with computers. This can be achieved using deep learning algorithms which are currently being used for various vision-based applications like self-driving vehicles. In this paper, we used the Convolutional Neural Network (CNN) for training and testing images with different facial expressions using the TensorFlow machine learning library. The application is comprised of two stages: a recognizer for validation purposes and a data training model that is used to train the data. The Data training model uses CNN to train data. With the help of this algorithm, the system can recognize the six universal emotions, anger, disgust, joy, surprise, sadness, and fear, along with neutral. The experiment demonstrated that the outcomes of the training program were significantly influenced by the image size that is used for training. As a result, both the RGB and grayscale images yielded comparable results, whereas images with different sizes exhibited variations in performance. The RGB images achieved a training accuracy of 99.666%, a validation accuracy of 99.95%, and a test accuracy of 32.28%, while the combination of RGB and grayscale images attained a training accuracy of 98.99%, a validation accuracy of 92.76%, and a test accuracy of 72.56%.