Abstract
Sign language is a form of visual-gestural communication that conveys semantic content through hand movements and postures. It comprises a structured set of gestures, each associated with specific meanings. For individuals with hearing impairments, sign language serves as a primary medium for expression, perception, and interaction with the external world. However, due to the general lack of sign language proficiency among the broader population, effective communication remains a significant challenge. This paper uses an RGB-D imaging device to capture both color and depth information of dynamic hand gestures, enabling more robust and discriminative feature extraction than traditional RGB-based approaches. The proposed system focuses on recognizing two-handed dynamic gestures by analyzing spatial configurations and temporal motion patterns. A gesture symbolization mechanism facilitates the recognition process, wherein complex gesture sequences are encoded into a set of primitive symbols representing key postures and transitions. These symbolic representations are then compared using a fuzzy matching algorithm, which accounts for variations in gesture execution and temporal alignment, thereby enhancing the system's tolerance. This methodology aims to provide a reliable and flexible framework for real-time gesture recognition in natural interaction scenarios.

This publication has 9 references indexed in Scilit: