Feature Extraction with Video Summarization of Dynamic Gestures for Peruvian Sign Language Recognition

Andre Neyra-Gutierrez, Pedro Shiguihara-Juarez

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

4 Scopus citations

Abstract

In peruvian sign language (PSL), recognition of static gestures has been proposed earlier. However, to state a conversation using sign language, it is also necessary to employ dynamic gestures. We propose a method to extract a feature vector for dynamic gestures of PSL. We collect a dataset with 288 video sequences of words related to dynamic gestures and we state a workflow to process the keypoints of the hands, obtaining a feature vector for each video sequence with the support of a video summarization technique. We employ 9 neural networks to test the method, achieving an average accuracy ranging from 80% and 90%, using 10 fold cross-validation.

Original languageEnglish
Title of host publicationProceedings of the 2020 IEEE 27th International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728193779
DOIs
StatePublished - Sep 2020
Externally publishedYes
Event27th IEEE International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2020 - Virtual, Lima, Peru
Duration: 3 Sep 20205 Sep 2020

Publication series

NameProceedings of the 2020 IEEE 27th International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2020

Conference

Conference27th IEEE International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2020
Country/TerritoryPeru
CityVirtual, Lima
Period3/09/205/09/20

Keywords

  • Dynamic Gestures
  • Feature Extraction
  • Peruvian Signal Language
  • Sign Language Recognition
  • Video Summarization

Fingerprint

Dive into the research topics of 'Feature Extraction with Video Summarization of Dynamic Gestures for Peruvian Sign Language Recognition'. Together they form a unique fingerprint.

Cite this