Outcome:
TDLC's Jim Tanaka (University of Victoria) and Marni Bartlett (UC San Diego's Machine Perception Lab) apply the LFI! Hierarchical Model of Facial Processing to better understand and improve the face processing skills of children with autism who sometimes struggle to recognize the identity and expression of a face. Following the model, the two teams designed the Let's Face It! computer program that guides the child through a series of exercises emphasizing attention to faces, recognition of facial identity and emotion and understanding the meaning of facial cues in a social context.

Impact/benefit:
In a recent randomized clinical trial published in the Journal of Child Psychiatry and Psychology (Tanaka et al., 2010), Tanaka found that children who played the Let's Face It! program for a minimum of 20 hours showed small, but consistent gains in their ability to use eye information in face recognition.


Explanation:
TDLC's Jim Tanaka (University of Victoria) and Marni Bartlett (UC San Diego's Machine Perception Lab) have joined forces to develop a new state-of the-art intervention treatment. Using their state-of-the-art Computer Expression Recognition Toolbox, they have created interactive games that interpret facial expressions in real time via webcam input. In SmileMaze, for example, the player overcomes obstacles in a labyrinth by producing smiles that are registered on the Smile-o-Meter. In Face-Face-Revolution, the player mimics a facial expression in synchrony to a disco beat. With these technological innovations, the two teams hope to develop new treatments in autism that make the giant leap from the computer screen to the real world of social engagement.

TDLC’s Jim Tanaka and Marni Bartlett

Additional article:

Marian Bartlett, Jim Tanaka, Javier Movellan, and Robert Schultz
UCSD, U. Victoria, CHOP

TDLC researchers are collaborating on an exciting new project intended to enhance the facial expression production abilities of children with autism. The new project integrates the computer-based intervention known as Let’s Face It! (LFI!) with UCSD’s Computer Expression Recognition Toolbox (CERT). Let’s Face It! (LFI!) is a training program designed to improve the face skills of children with autism in a variety of face processing domains. CERT is a revolutionary new software package that performs real-time expression detection via web-cam input. The integration of the LFI! program and CERT allows the child to receive immediate feedback on their facial expression productions. This technology has recently been implemented in an interactive exercise called "Smile Maze," in which users are required to produce and hold the target expression for varying lengths of time in order to navigate past obstacles located in a maze. Another new game, “Face-Face-Revolution” is modeled after the popular game Dance-Dance-Revolution, wehere the child is visually cued to produce the facial expressions of happy, angry, sad and disgusted. The motor production system may play a crucial role in the perception of visually presented facial expressions. The exercises developed by these TDLC researchers engage the production system, and may aid children with autism in learning nonverbal behaviors essential for social functioning.

Typically developing kids test the new face games
during Face Camp at University of Victoria.

Tanaka, J., Bartlett, M., Movellan, j., Littlewort, G., and Lee-Cultura, S. (2010). Face-Face-Revolution: A game in real-time facial expression recognition. Demo, Vision Sciences Society Conference, Naples, FL, May.

Cockburn, J., Bartlett, M., Tanaka, J., Movellan, J., Pierce, M., and Schultz, R. (2008). SmileMaze: A Tutoring System in Real-Time Facial Expression Perception and Production for Children with Autism Spectrum Disorder. Intl Conference on Automatic Face and Gesture Recognition, Workshop on Facial and Bodily expressions for Control and Adaptation of Games.