Learn More
We describe a new expression database which contains video sequences of both played and natural expressions and an expression classification system based on warped optical flow fields and texture features. We analyze the system's generalization performance when confronted with subjects that were not present in the training set and its recognition(More)
Despite the significant effort devoted to methods for expression recognition, suitable training and test databases designed explicitly for expression research have been largely neglected. Additionally, possible techniques for expression recognition within an Man-Machine-Interface (MMI) domain are numerous, but it remains unclear what methods are most(More)
  • 1