zjw-92/facial_emotion_detection

Facial emotion detection is the task of recognizing a person's emotional state among angry, disgust, fear, happy, neutral, sad and surprise using CNN deep learning technology.

Facial Emotion Detection

Facial Emotion Detection is the task of recognizing a person's emotional state among angry, disgust, fear, happy, neutral, sad and surprise using CNN deep learning technology.

Data source

All the data is downloaded from Kaggle FER-13.

Technologies

• Keras: A high-level, deep learning API for implementing neural networks.
• Tensorflow: An open-sourced end-to-end platform, a library for multiple machine learning tasks.
• OpenCV: A library of Python bindings designed to solve computer vision problems.
• Haar Cascade: An effective object detection method.
• CNN: Convolutional neural network, a kind of network architecture for deep learning algorithms and is specifically used for image recognition and tasks that involve the processing of pixel data.

Setup

• 1. Download dataset and put it in the directory
• 2. Open Pycharm terminal and run pip install -r requirements.txt

Train the model

Run python TrainEmotionDetection.py and emotion_model.json emotion_model.h5 will be gernerated after training.

Test the model

Run python TestEmotionDetection.py

Visualization