Emojify using face recognition with machine learning

What is Emojify ?
Emojify is used to detect your face expression like angry, fear , happy etc. After that this expression will send using tkinter toolkit in python.
This will help in online chatting ,brand emotions etc.

Now days is possible to detect the human emotions from the webcam and images using machine learning and deep learning. In deep learning and machine learning today`s world there are most of in built library available like keras and tensorflow .

Why jupyter notebook ?
Jupyter notebook is one of open source web application is used for live code,Visualizations and explanatory data. There are many task to do using jupyter notebook like data cleaning ,statistical modeling etc.

Project overview :-

We have done one project on Emojify using face recognition with machine learning and deep learning .In this project first we downloads the data set from kaggle (https://www.kaggle.com/msambare/fer2013). Data set will dividend into two category . 1.test data and 2. Train data. And also both of category dividend into seven part like that angry, disgust,fear,happy,natural,sad,surprise.All the seven folder is consists of 48x48 pixel grayscale images of faces.

Then after we load the dataset using keras. Preprocessing.image.
After that we create convolutional neural network using keras layer. Below you can how the model will train layer by layer.

Fig. CNN Model

Above image you see that we use four conv2D layer and one flatten layer ,two dense layer. we have to generate output using Soft max equation.
After that we calculate accuracy of our train model. Also below you can show that hall accuracy, loss, validation accuracy and validation loss.

Fig. Epoch 1 to 10

Fig. Epoch 11 to 20

Fig. Epoch 21 to 25

Now when we increase the Epoch at that time accuracy will be increase and loss will be decrease.
Now we save our model using save_weights function.

Fig. Save Model

After that we have open webcam using open cv and detect face using CascadeClassifier .Then after predict the emotions. Out put is Below.

Fig. Detect the angry face

Fig. Detect the fear face

Summary
We learned to detect faces expression in deep learning and how to build Convolutional neural network using keras and find out the accuracy of our model.

I hope you enjoyed this project.

Source Code:-
https://github.com/YagnikBavishi/Emojify-using-face-recognition-with-ml-dl