Py Emotion
Human facial emotion recognition using OpenCV Deep Neural Networks (DNN)
By Laurent Ittiitti@usc.eduhttp://jevois.orgGPL v3
 Language: PythonSupports mappings with USB output: YesSupports mappings with NO USB output: No 
 Video Mapping:   YUYV 320 336 15.0 YUYV 320 336 15.0 JeVois PyEmotion

Module Documentation

This module runs an emotion classification deep neural network using the OpenCV DNN library. The network is from the FER+ emotion recognition project, "Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution" arXiv:1608.01041

The module outputs a score from -1000 to 1000 for each of: neutral, happiness, surprise, sadness, anger, disgust, fear, contempt.

Note that this module does not include any face detection. Hence it always assumes that there is a face well centered in the image. You should enhance this module with first applying a face detector (see, e.g., PyDetectionDNN) and to only run the emotion recognition network on the detected faces.

ParameterTypeDescriptionDefaultValid Values
This module exposes no parameter
Detailed docs:PyEmotion
Copyright:Copyright (C) 2019 by Laurent Itti
License:GPL v3
Support URL:
Other URL:
Address:880 W 1st St Suite 807, Los Angeles CA 90012, USA