On Line Emotion Detection Using Retrainable Deep Neural Networks

This paper presents a new methodology for detecting deterioration in performance of deep neural networks when applied to on line visual analysis problems and enabling fine-tuning, or retraining, of the network to the current data characteristics. Pre-trained deep neural networks which have a satisfactory performance on the problem under study constitute the basis of the approach, with efficient transfer learning being performed whenever drift is detected in network operation. The method is applied and validated on the problem of emotion detection using line facial expression analysis based on a dimensional emotion representation.