Abstract:
Over the last years, there is a large number of studies focused in automatic facial
expression analysis because of its practical importance in many human-computer
interaction Systems. With the transition of facial expression recognition (FER) from
laboratory-controlled to challenging in-the-wild conditions and the recent success of
deep learning techniques in various fields, deep neural networks have increasingly
been leveraged to learn discriminative representations for automatic FER. In this
thesis, we study the challenges of Emotion Recognition Datasets and try different
parameters and architectures of the Conventional Neural Networks. The dataset we
have used is iCV MEFED, a relatively new, interesting and very challenging.
