Facial expressions detection

This project detects human facial expressions using Deep Learning and Computer Vision

Here's a snippet

About the Project

• Using TensorFlow, I have created a deep learning ConvNet Model detection_model.h5 to detect Happy, Sad, Angry and Surprised facial expressions.

• The model is trained on the FER-2013 Kaggle Dataset.

• You can find the model building and training process in the model_training.ipynb file.

• Using OpenCV and Python, I have extracted the facial features with the help of Haar Cascade Classifier haarcascade_frontalface_default.xml, and given them to my model to detect the expressions.

• I have written two Python scripts viz. detection_on_vid.py and detection_on_image.py. The former detects facial expressions using Webcam and the latter detects the facial expressions in an image.

Libraries Used

• TensorFlow 2.0

• Keras

• OpenCV

• Python>=3.7

• Numpy

Here's what you can do to use this project to detect your facial expressions using the webcam:

Make sure you have Python>=3.7 installed in your machine, if not then you can download it here.

1. Clone this repo or download the zip folder.

2. Go to the directory of this repo cloned or downloaded onto your local machine and open cmd.

3. Install the dependencies by running requirements.txt file in cmd.

4. Run detection_on_vid.py file and try making different expressions like Happy, Sad, Angry and Surprised faces and notice the detections made.