In this work, we present ChildSafe, a classification sys- Tem which exploits human skeletal features collected us- ing a 3D depth camera to classify visual characteristics between children and adults. ChildSafe analyzes the histograms of training samples and implements a bin- boundary-based classifier. We train and evaluate Child- Safe using a large dataset of visual samples collected from 150 elementary school children and 43 adults, rang- ing in the ages of 7 and 50. Our results suggest that ChildSafe successfully detects children with a proper classification rate of up to 97%, a false negative rate of as low as 1.82%, and a low false positive rate of 1.46%. We envision this work as an effective sub-system for de- signing various child protection applications.
|Title of host publication||UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing|
|Publisher||Association for Computing Machinery, Inc|
|Number of pages||5|
|Publication status||Published - 2014|
|Event||2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014 - Seattle, United States|
Duration: 2014 Sept 13 → 2014 Sept 17
|Name||UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing|
|Other||2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014|
|Period||14/9/13 → 14/9/17|
Bibliographical notePublisher Copyright:
Copyright © 2014 by the Association for Computing Machinery, Inc. (ACM).
All Science Journal Classification (ASJC) codes