Hand and wrist localization approach for features extraction in Arabic sign language recognition

Sana Fakhfakh, Yousra Ben Jemaa

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

6 Scopus citations

Abstract

This paper proposes a new hand detection and wrist localization method which presents an important step in the hand gesture recognizing process. The wrist localization step has not been given much attention and the existing works are limited and include many conditions.Our proposed approach was evaluated on a public dataset whose obtained results underscore its performance. We highlight through a comparative study with existing work, the superiority of our approach and the importance of the wrist localization step. We also propose to benefit from our proposed method which can be applied in the sign language recognition domain, and more precisely in the Arabic digit sign language recognition.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE/ACS 14th International Conference on Computer Systems and Applications, AICCSA 2017
PublisherIEEE Computer Society
Pages774-780
Number of pages7
ISBN (Electronic)9781538635810
DOIs
StatePublished - 2 Jul 2017
Externally publishedYes
Event14th IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2017 - Hammamet, Tunisia
Duration: 30 Oct 20173 Nov 2017

Publication series

NameProceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA
Volume2017-October
ISSN (Print)2161-5322
ISSN (Electronic)2161-5330

Conference

Conference14th IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2017
Country/TerritoryTunisia
CityHammamet
Period30/10/173/11/17

Keywords

  • Arab Sign Language
  • Gesture recognition
  • Hand segmentation
  • Shape descriptor
  • Wrist localization

Fingerprint

Dive into the research topics of 'Hand and wrist localization approach for features extraction in Arabic sign language recognition'. Together they form a unique fingerprint.

Cite this