Published Paper Details:

Machine learning and deep learning techniques currently are leveraged by various practitioners in computer vision field. This thesis proposes an application of two different machine learning models to classify facial expressions of human and replace them with emoji's accordingly. An application that can turn face expression into emoji's. For that I have train machine learning model with TensorFlow to detect face expression like happy, sad, fearful and so one. Then I have map those expression to emoji's in real times. In this project I used media pip for the key point's extraction. The key points of face, left and right hand are extracted using media pipe. The first model is based on fisher-face algorithm which is used for face recognition, the second one is a simplified version of prevalent Convolution Neural Network model utilized by many researchers: VGGNet network. The former model is implemented on OpenCV library, whereas convolutional neural network is build with help of Keras. I trained both models by an open source dataset (Kaggle) which divides its facial expression images into 43 classes. Both models are tested with randomly selected images of facial expression from internet Overall training accuracy is 94% in the phase of training