Towards intent-aware and privacy-preserving image processing systems

Jake O'Donnell; Jason Tan; Radu-Casian Mihailescu

doi:10.1145/3423423.3423426

Towards intent-aware and privacy-preserving image processing systems

Jake O'Donnell, Jason Tan, Radu-Casian Mihailescu

School of Mathematical & Computer Sciences

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

Abstract

Biometric solutions for access control is an active line of research. Specifically, when it comes to facial identification for access control, these systems can pose privacy concerns. For instance, identifying people that do not want to use the facial identification module. This work focuses on implementing an intent-aware system, which uses a hand gesture trigger to initiate the identification process. In order to evaluate the system, test cases were performed to verify accuracy of each hand gesture. Thereafter, a scenario was created to simulate an activation of the prototype system. The evaluation was used to determine the convenience and guidance when implementing intent-aware systems.

Original language	English
Title of host publication	IoT '20 Companion: Companion Proceedings of the 10th International Conference on the Internet of Things
Publisher	Association for Computing Machinery
ISBN (Print)	9781450388207
DOIs	https://doi.org/10.1145/3423423.3423426
Publication status	Published - 6 Oct 2020
Event	10th International Conference on the Internet of Things 2020 - Virtual, Online, Sweden Duration: 6 Oct 2020 → 9 Oct 2020

Conference

Conference	10th International Conference on the Internet of Things 2020
Abbreviated title	IoT 2020
Country/Territory	Sweden
City	Virtual, Online
Period	6/10/20 → 9/10/20

Keywords

Computer vision
Hand gesture
Human-computer interaction
Intent-trigger

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3423423.3423426

Cite this

@inproceedings{57c3ed287aa247b89d75aa26ae89bdb1,

title = "Towards intent-aware and privacy-preserving image processing systems",

abstract = "Biometric solutions for access control is an active line of research. Specifically, when it comes to facial identification for access control, these systems can pose privacy concerns. For instance, identifying people that do not want to use the facial identification module. This work focuses on implementing an intent-aware system, which uses a hand gesture trigger to initiate the identification process. In order to evaluate the system, test cases were performed to verify accuracy of each hand gesture. Thereafter, a scenario was created to simulate an activation of the prototype system. The evaluation was used to determine the convenience and guidance when implementing intent-aware systems.",

keywords = "Computer vision, Hand gesture, Human-computer interaction, Intent-trigger",

author = "Jake O'Donnell and Jason Tan and Radu-Casian Mihailescu",

note = "Publisher Copyright: {\textcopyright} 2020 ACM.; 10th International Conference on the Internet of Things 2020, IoT 2020 ; Conference date: 06-10-2020 Through 09-10-2020",

year = "2020",

month = oct,

day = "6",

doi = "10.1145/3423423.3423426",

language = "English",

isbn = "9781450388207",

booktitle = "IoT '20 Companion: Companion Proceedings of the 10th International Conference on the Internet of Things",

publisher = "Association for Computing Machinery",

address = "United States",

}

O'Donnell, J, Tan, J & Mihailescu, R-C 2020, Towards intent-aware and privacy-preserving image processing systems. in IoT '20 Companion: Companion Proceedings of the 10th International Conference on the Internet of Things., 3, Association for Computing Machinery, 10th International Conference on the Internet of Things 2020, Virtual, Online, Sweden, 6/10/20. https://doi.org/10.1145/3423423.3423426

TY - GEN

T1 - Towards intent-aware and privacy-preserving image processing systems

AU - O'Donnell, Jake

AU - Tan, Jason

AU - Mihailescu, Radu-Casian

PY - 2020/10/6

Y1 - 2020/10/6

N2 - Biometric solutions for access control is an active line of research. Specifically, when it comes to facial identification for access control, these systems can pose privacy concerns. For instance, identifying people that do not want to use the facial identification module. This work focuses on implementing an intent-aware system, which uses a hand gesture trigger to initiate the identification process. In order to evaluate the system, test cases were performed to verify accuracy of each hand gesture. Thereafter, a scenario was created to simulate an activation of the prototype system. The evaluation was used to determine the convenience and guidance when implementing intent-aware systems.

AB - Biometric solutions for access control is an active line of research. Specifically, when it comes to facial identification for access control, these systems can pose privacy concerns. For instance, identifying people that do not want to use the facial identification module. This work focuses on implementing an intent-aware system, which uses a hand gesture trigger to initiate the identification process. In order to evaluate the system, test cases were performed to verify accuracy of each hand gesture. Thereafter, a scenario was created to simulate an activation of the prototype system. The evaluation was used to determine the convenience and guidance when implementing intent-aware systems.

KW - Computer vision

KW - Hand gesture

KW - Human-computer interaction

KW - Intent-trigger

UR - https://www.scopus.com/pages/publications/85123040499

U2 - 10.1145/3423423.3423426

DO - 10.1145/3423423.3423426

M3 - Conference contribution

AN - SCOPUS:85123040499

SN - 9781450388207

BT - IoT '20 Companion: Companion Proceedings of the 10th International Conference on the Internet of Things

PB - Association for Computing Machinery

T2 - 10th International Conference on the Internet of Things 2020

Y2 - 6 October 2020 through 9 October 2020

ER -

Towards intent-aware and privacy-preserving image processing systems

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this