Current solutions for American sign language users have been limited to a human translator.
Through our design, we have employed two machine learning models. First, a visual transcript of hand signs, and other physical features must be established, and accurately return a string of words. Yet, such words are not grammatically legible for English speakers. A second natural language processing model must therefore be created to palliate this translation barrier. Such models have been trained through rigorously treated datasets limiting the necessary processing input, and may later be encapsulated in a mobile application, directly using a phone’s camera.

Infos

Participants

• Xin Lei Lin
• Aly Shariff

Année : 2023

Région : Montreal Regional Science & Technology Fair (Sec/Coll)

Type de projet : C

Classe : C1

Categorie de projet : IIR

Volet : Collegial

Niveau scolaire : Collégial 1

École : Marianopolis College

Prix et distinctions

Finale Québécoise

Montréal,CEPSUM

• Médaille du Réseau Technoscience - Bronze Collégial
• Prix du minstère de l'Économie, de l'Innovation et de l'Énergie