American Sign Language (ASL) to voice translation system using the blackfin microprocessor

Date of Publication

2010

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Electronics and Communications Engineering

College

Gokongwei College of Engineering

Department/Unit

Electronics and Communications Engineering

Thesis Adviser

Cesar A. Llorente

Defense Panel Chair

Gerino P. Mappatao

Defense Panel Member

Lawrence Y. Materum

Roberto T. Caguinguin

Abstract/Summary

This paper discusses an approach for capturing and translating American Sign Language into voice using the Blackfin Microprocessor. The instrumentation parts of the system consist of the flexion sensors along the fingers, the wrist and the elbow. Also, accelerometers are positioned in the forearm near the wrist, and in the arm near the elbow. Gestures of the American Sign Language are broken down into phonemes of poses and movements. The poses defined by the study are composed of at least 26 handshapes, 9 signing space and 5 core palm orientations. Training was accomplished by doing several sets of the different states of the pose. Recognition rates of modularized states of the different components of the pose proved that the system is capable of recognizing the different states relatively well.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU15539

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

159, [113] leaves : ill. ; 28 cm.

Keywords

American Sign Language--Translating

This document is currently not available here.

Share

COinS