Analysis of Head-Mounted Wireless Camera Videos for Early Diagnosis of Autism

In this paper we present a computer based approach to analysis of social interaction experiments for the diagnosis of autism spectrum disorders in young children of 6-18 months of age. We apply face detection on videos from a head-mounted wireless camera to measure the time a child spends looking at people. In-Plane rotation invariant Face Detection is used to detect faces from the diverse directions of the children’s head. Skin color detection is used to render the system more robust to cluttered environments and to the poor quality of the video recording.