The paper shows a system for automatic recognition of Signed It alian sentences. The proposed system is based on a multi-level architecture that m odels and manages the knowledge involved in the recognition process in a simple and robust way, integrating a common sense engine in order to deal with sentences in their context. In this architecture, the higher abstraction level introd uces a semantic control and an analysis of the correctness of a sentence given a sequence of previously recognized signs. Experimenta tions are presented using a set of signs from the Italian Sign Language (LIS) and a sentence template usef ul for domotic applications, an d show a high recognition rate that encourages to investigate on larger set of sign and more general contexts.
A Software System for Automatic Signed Italian Recognition
Infantino Ignazio;Rizzo Riccardo;
2006
Abstract
The paper shows a system for automatic recognition of Signed It alian sentences. The proposed system is based on a multi-level architecture that m odels and manages the knowledge involved in the recognition process in a simple and robust way, integrating a common sense engine in order to deal with sentences in their context. In this architecture, the higher abstraction level introd uces a semantic control and an analysis of the correctness of a sentence given a sequence of previously recognized signs. Experimenta tions are presented using a set of signs from the Italian Sign Language (LIS) and a sentence template usef ul for domotic applications, an d show a high recognition rate that encourages to investigate on larger set of sign and more general contexts.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
