Scratch nodes ML: A playful system for children to create gesture recognition classifiers

Adam Agassi, Iddo Yehoshua Wald, Hadas Erel, Oren Zuckerman

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

39 Scopus citations

Abstract

Children are growing up in a Machine Learning infused world and it's imperative to provide them with opportunities to develop an accurate understanding of basic Machine Learning concepts. Physical gesture recognition is a typical application of Machine Learning, and physical gestures are also an integral part of children's lives, including sports and play. We present Scratch Nodes ML, a system enabling children to create personalized gesture recognizers by: (1) Creating their own gesture classes; (2) Collecting gesture data for each class; (3) Evaluating the classifier they created with new gesture data; (4) Integrating their classifiers into the Scratch environment as new Scratch blocks, empowering other children to use these new blocks as gesture classifiers in their own Scratch creations.

Original languageEnglish
Title of host publicationCHI EA 2019 - Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450359719
DOIs
StatePublished - 2 May 2019
Externally publishedYes
Event2019 CHI Conference on Human Factors in Computing Systems, CHI EA 2019 - Glasgow, United Kingdom
Duration: 4 May 20199 May 2019

Publication series

NameConference on Human Factors in Computing Systems - Proceedings

Conference

Conference2019 CHI Conference on Human Factors in Computing Systems, CHI EA 2019
Country/TerritoryUnited Kingdom
CityGlasgow
Period4/05/199/05/19

Keywords

  • Children
  • Gesture Recognition
  • Machine Learning

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Scratch nodes ML: A playful system for children to create gesture recognition classifiers'. Together they form a unique fingerprint.

Cite this