British sign language recognition in the wild based on multi-class SVM

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Citations (Scopus)
266 Downloads (Pure)

Abstract

Developing assistive, cost-effective, non-invasive technologies to aid communication of people with hearing impairments is of prime importance in our society, in order to widen accessibility and inclusiveness. For this purpose, we have developed an intelligent vision system embedded on a smartphone and deployed in the wild. In particular, it integrates both computer vision methods involving Histogram of Oriented Gradients (HOG) and machine learning techniques such as multiclass Support Vector Machine (SVM) to detect and recognize British Visual Language (BSL) signs automatically. Our system was successfully tested on a real-world dataset containing 13,066 samples and shown an accuracy of over 99\% with an average processing time of 170ms, thus appropriate for real-time visual signing.
Original languageEnglish
Title of host publicationProceedings of the 2019 Federated Conference on Computer Science and Information Systems
EditorsMaria Ganzha, Leszek Maciaszek, Marcin Paprzycki
PublisherIEEE
Pages81-86
Number of pages6
ISBN (Electronic)9788395235788, 9788395235795
ISBN (Print)9788395541605
DOIs
Publication statusPublished - 4 Sep 2019
Event14th Federated Conference on Computer Science and Information Systems - Leipzig University , Leipzig , Germany
Duration: 1 Sep 20194 Sep 2019
Conference number: 14
https://fedcsis.org/

Publication series

NameAnnals of Computer Science and Information Systems
PublisherIEEE
Volume18
ISSN (Electronic)2300-5963

Conference

Conference14th Federated Conference on Computer Science and Information Systems
Abbreviated titleFedCSIS
Country/TerritoryGermany
CityLeipzig
Period1/09/194/09/19
Internet address

Fingerprint

Dive into the research topics of 'British sign language recognition in the wild based on multi-class SVM'. Together they form a unique fingerprint.

Cite this