Facial expressions Recognition using CNN
- Used CNN to build a Model which can Learn facial expressions from an image. The Model was Trained on the famous FER-2013 Dataset present on Kaggle.
- The data consists of 48x48 pixel grayscale images of faces.
- The task is to categorize each face based on the emotion shown in the facial expression into one of seven categories : (0=Angry, 1=Disgust, 2=Fear, 3=Happy, 4=Sad, 5=Surprise, 6=Neutral).
- The training set consists of 28,709 examples and the public test set consists of 3,589 examples.
- The Base CNN Model Achieved an Accuracy of 35.60 but on further improvement using Hyperparameter Tuning, Augmentation , Transfer Learning I was able to achieve accuracy of 65% Using the VGG19 model.