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

Matthew Quinn; Joanna Isabelle Olszewska

doi:10.15439/2019F274

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

Matthew Quinn
, Joanna Isabelle Olszewska

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

18 Citations (Scopus)

304 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 language	English
Title of host publication	Proceedings of the 2019 Federated Conference on Computer Science and Information Systems
Editors	Maria Ganzha, Leszek Maciaszek, Marcin Paprzycki
Publisher	IEEE
Pages	81-86
Number of pages	6
ISBN (Electronic)	9788395235788, 9788395235795
ISBN (Print)	9788395541605
DOIs	https://doi.org/10.15439/2019F274
Publication status	Published - 4 Sept 2019
Event	14th Federated Conference on Computer Science and Information Systems - Leipzig University , Leipzig , Germany Duration: 1 Sept 2019 → 4 Sept 2019 Conference number: 14 https://fedcsis.org/

Publication series

Name	Annals of Computer Science and Information Systems
Publisher	IEEE
Volume	18
ISSN (Electronic)	2300-5963

Conference

Conference	14th Federated Conference on Computer Science and Information Systems
Abbreviated title	FedCSIS
Country/Territory	Germany
City	Leipzig
Period	1/09/19 → 4/09/19
Internet address	https://fedcsis.org/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 4 Quality Education
SDG 9 Industry, Innovation, and Infrastructure
SDG 16 Peace, Justice and Strong Institutions

Access to Document

10.15439/2019F274

2019 07 17 Olszewska et al British FinalFinal published version, 787 KB

https://ieeexplore.ieee.org/document/8860003

Joanna Olszewska
Person

Cite this

@inproceedings{ed9bb529f05f40628297d6a13d438bb6,

title = "British sign language recognition in the wild based on multi-class SVM",

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.",

author = "Matthew Quinn and Olszewska, \{Joanna Isabelle\}",

year = "2019",

month = sep,

day = "4",

doi = "10.15439/2019F274",

language = "English",

isbn = "9788395541605",

series = "Annals of Computer Science and Information Systems",

publisher = "IEEE",

pages = "81--86",

editor = "Maria Ganzha and Leszek Maciaszek and Marcin Paprzycki",

booktitle = "Proceedings of the 2019 Federated Conference on Computer Science and Information Systems",

address = "United States",

note = "14th Federated Conference on Computer Science and Information Systems, FedCSIS ; Conference date: 01-09-2019 Through 04-09-2019",

url = "https://fedcsis.org/",

}

Quinn, M & Olszewska, JI 2019, British sign language recognition in the wild based on multi-class SVM. in M Ganzha, L Maciaszek & M Paprzycki (eds), Proceedings of the 2019 Federated Conference on Computer Science and Information Systems. Annals of Computer Science and Information Systems, vol. 18, IEEE, pp. 81-86, 14th Federated Conference on Computer Science and Information Systems, Leipzig , Germany, 1/09/19. https://doi.org/10.15439/2019F274

British sign language recognition in the wild based on multi-class SVM. / Quinn, Matthew; Olszewska, Joanna Isabelle.
Proceedings of the 2019 Federated Conference on Computer Science and Information Systems. ed. / Maria Ganzha; Leszek Maciaszek; Marcin Paprzycki. IEEE, 2019. p. 81-86 (Annals of Computer Science and Information Systems; Vol. 18).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - British sign language recognition in the wild based on multi-class SVM

AU - Quinn, Matthew

AU - Olszewska, Joanna Isabelle

N1 - Conference code: 14

PY - 2019/9/4

Y1 - 2019/9/4

N2 - 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.

AB - 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.

U2 - 10.15439/2019F274

DO - 10.15439/2019F274

M3 - Conference contribution

SN - 9788395541605

T3 - Annals of Computer Science and Information Systems

SP - 81

EP - 86

BT - Proceedings of the 2019 Federated Conference on Computer Science and Information Systems

A2 - Ganzha, Maria

A2 - Maciaszek, Leszek

A2 - Paprzycki, Marcin

PB - IEEE

T2 - 14th Federated Conference on Computer Science and Information Systems

Y2 - 1 September 2019 through 4 September 2019

ER -

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

Abstract

Publication series

Conference

UN SDGs

Access to Document

Fingerprint

Profiles

Joanna Olszewska

Cite this