We explore recognition implications of understanding gesture communication, having chosen American sign language as an example of a gesture language. An instrumented glove and specially developed software have been used for data collection and labeling. We address the problem of recognizing dynamic signing, i.e. signing performed at natural speed. Two neural network architectures have been used for recognition of different types of finger-spelled sentences. Experimental results are presented suggesting that two features of signing affect recognition accuracy: signing frequency which to a large extent can be accounted for by training a network on the samples of the respective frequency; and coarticulation effect which a network fails to identify. As a possible solution to coarticulation problem two post-processing algorithms for temporal segmentation are proposed and experimentally evaluated.

The system described uses frame buffers to provide digital analogues to the traditional processes of copying pencil drawings onto cels, painting them, and photographing them. The copying process is replaced by scanning the pencil drawings with a television camera and digitizing the video signal. Several image processing operations are performed on the digitized drawings to condition them for the next step, interactive painting of the drawings mediated by a computer program. The painted drawings are then combined with each other and painted backgrounds for frame by frame recording on film or video tape.