Group-level Emotion Recognition using Transfer Learning from Face Identification
Preprint
Abstract
In this paper, we describe our algorithmic approach, which was used for submissions in the fifth Emotion Recognition in the Wild (EmotiW 2017) group-level emotion recognition sub-challenge. We extracted feature vectors of detected faces using the Convolutional Neural Network trained for face identification task, rather than traditional pre-training on emotion recognition problems. In the final pipeline an ensemble of Random Forest classifiers was learned to predict emotion score using available training set. In case when the faces have not been detected, one member of our ensemble extracts features from the whole image. During our experimental study, the proposed approach showed the lowest error rate when compared to other explored techniques. In particular, we achieved 75.4% accuracy on the validation data, which is 20% higher than the handcrafted feature-based baseline. The source code using Keras framework is publicly available.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Video-based emotion recognition in the wild using deep transfer learning and score fusionImage and Vision Computing, 2017
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Maximum-likelihood approximate nearest neighbor method in real-time image recognitionPattern Recognition, 2017
- Search Techniques in Intelligent Classification Systems2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Automatic Analysis of Facial Affect: A Survey of Registration, Representation, and RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014