Paper

"A Robust Facial Expression Recognition Algorithm Based on Multi-Rate Feature Fusion Scheme" Sensors (MDPI) at online: https://doi.org/10.3390/s21216954

Model Stucture

Installation (Environment)

• python 3.7

- pip install tensorflow-gpu==2.1.0
- pip install keras==2.2.4
- pip install theano
- pip install opencv-python
- pip install matplotlib
- pip install numpy
- pip install keras-self-attention

• Install ‘FaceBoxes’ module’s environment for face detection
  ( https://github.com/sfzhang15/FaceBoxes )
• Install ’SAN’ module’s environment for landmark detection
  ( https://github.com/D-X-Y/landmark-detection )

Train and Test

concat_train_test.py

• first input = selected dataset you want to train and test from the above list
• second input = iteration of training & testing preprocessing list (pre = ['pre', 'lbp', 'norm', 'normlbp'])

EXAMPLE

python concat_train_test.py   

then enter

1   

and enter

3   

it means

• first input : 1 -> select 'MMI_minimum dataset'
• second input : 3 -> train & test selected database of 'preprocessed, lbp, normalized dataset'