An image acquisition unit of an information processing device acquires data for a moving image including an image of a user and captured by an image capturing device. A tracking processing unit uses a particle filter to perform visual tracking in the moving image so as to estimate a head contour of the user. A gesture detection unit identifies a facial region in an area inside the head contour, acquires a parameter indicating the orientation of the face, and keeping a history of parameters. When time-dependent change in the orientation of the face meets a predetermined criterion, it is determined that a gesture is made. The output data generation unit generates output data dependent on a result of detecting a gesture. The output control unit controls the generated output data so as to display the data on the display, for example.