High accuracy character recognition techniques can provide useful information for segmentation-based handwritten word recognition systems. This research describes neural network-b...
In this paper, we propose a new character generation method from on-line handwriting recognizers based on Bayesian networks. On-line handwriting recognizers are trained with handw...
We study the use of kernel subspace methods for learning low-dimensional representations for classification. We propose a kernel pooled local discriminant subspace method and com...
Tracing and performance analysis tools are an important component in the development of high performance applications. Tracing parallel programs with current tracing tools, howeve...
We introduce a facial animation system that produces real-time animation sequences including speech synchronization and non-verbal speech-related facial expressions from plain tex...