Home

Facial_Expression_Recognition_FER2013

Powered by Python 3.5

Libray Requirements

 pip install tensorflow-gpu
 pip install keras
 pip install numpy
 pip install sklearn
 pip install pandas
 pip install opencv-python

Dataset

FER2013 Kaggle Challenge - https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data

Accuracy Achivement

Kaggle Challenge Winner 71.2%.

Model Combine CNN1 + CNN2 + CNN-FAST + CNN_SIFT 72.89%

Confusion Matrix

CNN Architectures

Build from scratch in /cnn folder .

HOW ARE YOU TO DAY? Application

You can choose some image and video that include human faces to detect emotions

Click Button "Open Your Camera" for real-time detecting yourself emotions from webcam.

Highlight Results

Video Realtime

Example will be uploaded later.