Work

3DZSignDB: 3D avatar SigML data for Algerian sign language

Year: 2025

Type: data-paper

Abstract: We present a dataset of Algerian Sign Language (ALSL) used to develop a translation system into a 3D avatar. We used the Notation System Method, which is mostly based on the Hamburg Notation System (HamNoSys), to encode 417 ALSL lexical signs. The data collection process involved collaboration with ALSL translation experts to ensure the consistency of sign representations. NSM transcribed each sign, capturing essential linguistic features such as hand shape, movement, and facial expressions. The resulting dataset was used for a real-time translation system that converts written Arabic words into sign language represented by a 3D avatar. Applications for the dataset include sign language education and assistive technologies for the deaf community. You can use it to improve systems for automatic sign language translation. The structured and annotated ALSL lexicon that is provided helps with the ongoing development of technologies that allow everyone to communicate and with making more progress in recognizing and synthesizing sign language.

Source: Data in Brief

DOI: 10.1016/j.dib.2025.111568

Authors: Taha Zerrouki, Mohamed Fares Slimani, Amine Mami, Redha Mazari

Institutions: University of Bouira, University of Boumerdes, University Yahia Fares of Medea

Language: English

Topic: Hand Gesture Recognition Systems

Subfield: Human-Computer Interaction

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,220

OpenAlex ID: W4409800740

Cites: 13

Cited by: 3

Related to: 10