This paper describes an approach to providing lexical information for natural language processing in unrestricted domains. A system of approximately 1200 morphological rules is us...
A novel algorithm for motion segmentation is proposed. The algorithm uses the fact that shape of an object with homogeneous motion is represented as 4 dimensional linear space. Th...
Recognition using only visual evidence cannot always be successful due to limitations of information and resources available during training. Considering relation among lexicon en...
We propose a face difference model that decomposes face difference into three components, intrinsic difference, transformation difference, and noise. Using the face difference mod...
A new probabilistic background model based on a Hidden Markov Model is presented. The hidden states of the model enable discrimination between foreground, background and shadow. Th...