A Model for Inebriation Recognition in Humans Using Computer Vision

Zibusiso Bhango; Dustin van der Haar

doi:10.1007/978-3-030-20485-3_20

A Model for Inebriation Recognition in Humans Using Computer Vision

Zibusiso Bhango
, Dustin van der Haar

Academy of Computer Science and Software Engineering

University of Johannesburg

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

2 Citations (Scopus)

Abstract

The cost of substance use regarding lives lost, medical and psychiatric morbidity and social disruptions by far surpasses the economic costs. Alcohol abuse and dependence has been a social issue in need of addressing for centuries now. Methods exist that attempt to solve this problem by recognizing inebriation in humans. These methods include the use of blood tests, breathalyzers, urine tests, ECGs and wearables devices. Although effective, these methods are very inconvenient for the user, and the required equipment is expensive. We propose a method that provides a faster and convenient way to recognize inebriation. Our method uses Viola-Jones-based face-detection for the region of interest. The face images become input to a Convolutional Neural Network (CNN) which attempts to classify inebriation. In order to test our model’s performance against other methods, we implemented Local Binary Patterns (LBP) for feature extraction, and Support Vector Machines (SVM), Gaussian Naive Bayes (GNB) and k-Nearest Neighbor (kNN) classifiers. Our model had an accuracy rate of 84.31% and easily outperformed the other methods.

Original language	English
Title of host publication	Business Information Systems - 22nd International Conference, BIS 2019, Proceedings
Editors	Witold Abramowicz, Rafael Corchuelo
Publisher	Springer Verlag
Pages	259-270
Number of pages	12
ISBN (Print)	9783030204846
DOIs	https://doi.org/10.1007/978-3-030-20485-3_20
Publication status	Published - 2019
Event	22nd International Conference on Business Information Systems, BIS 2019 - Seville, Spain Duration: 26 Jun 2019 → 28 Jun 2019

Publication series

Name	Lecture Notes in Business Information Processing
Volume	353
ISSN (Print)	1865-1348
ISSN (Electronic)	1865-1356

Conference

Conference	22nd International Conference on Business Information Systems, BIS 2019
Country/Territory	Spain
City	Seville
Period	26/06/19 → 28/06/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Computer vision
Convolutional Neural Networks
Inebriation recognition
k-Nearest Neighbor
Machine learning
Naive Bayes
Support Vector Machines

ASJC Scopus subject areas

Management Information Systems
Control and Systems Engineering
Business and International Management
Information Systems
Modeling and Simulation
Information Systems and Management

Access to Document

10.1007/978-3-030-20485-3_20

Cite this

Bhango, Z., & van der Haar, D. (2019). A Model for Inebriation Recognition in Humans Using Computer Vision. In W. Abramowicz, & R. Corchuelo (Eds.), Business Information Systems - 22nd International Conference, BIS 2019, Proceedings (pp. 259-270). (Lecture Notes in Business Information Processing; Vol. 353). Springer Verlag. https://doi.org/10.1007/978-3-030-20485-3_20

@inproceedings{da9eb563fd424e0f8fd136cbb54c6816,

title = "A Model for Inebriation Recognition in Humans Using Computer Vision",

abstract = "The cost of substance use regarding lives lost, medical and psychiatric morbidity and social disruptions by far surpasses the economic costs. Alcohol abuse and dependence has been a social issue in need of addressing for centuries now. Methods exist that attempt to solve this problem by recognizing inebriation in humans. These methods include the use of blood tests, breathalyzers, urine tests, ECGs and wearables devices. Although effective, these methods are very inconvenient for the user, and the required equipment is expensive. We propose a method that provides a faster and convenient way to recognize inebriation. Our method uses Viola-Jones-based face-detection for the region of interest. The face images become input to a Convolutional Neural Network (CNN) which attempts to classify inebriation. In order to test our model{\textquoteright}s performance against other methods, we implemented Local Binary Patterns (LBP) for feature extraction, and Support Vector Machines (SVM), Gaussian Naive Bayes (GNB) and k-Nearest Neighbor (kNN) classifiers. Our model had an accuracy rate of 84.31\% and easily outperformed the other methods.",

keywords = "Computer vision, Convolutional Neural Networks, Inebriation recognition, k-Nearest Neighbor, Machine learning, Naive Bayes, Support Vector Machines",

author = "Zibusiso Bhango and \{van der Haar\}, Dustin",

note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature Switzerland AG.; 22nd International Conference on Business Information Systems, BIS 2019 ; Conference date: 26-06-2019 Through 28-06-2019",

year = "2019",

doi = "10.1007/978-3-030-20485-3\_20",

language = "English",

isbn = "9783030204846",

series = "Lecture Notes in Business Information Processing",

publisher = "Springer Verlag",

pages = "259--270",

editor = "Witold Abramowicz and Rafael Corchuelo",

booktitle = "Business Information Systems - 22nd International Conference, BIS 2019, Proceedings",

address = "Germany",

}

Bhango, Z & van der Haar, D 2019, A Model for Inebriation Recognition in Humans Using Computer Vision. in W Abramowicz & R Corchuelo (eds), Business Information Systems - 22nd International Conference, BIS 2019, Proceedings. Lecture Notes in Business Information Processing, vol. 353, Springer Verlag, pp. 259-270, 22nd International Conference on Business Information Systems, BIS 2019, Seville, Spain, 26/06/19. https://doi.org/10.1007/978-3-030-20485-3_20

A Model for Inebriation Recognition in Humans Using Computer Vision. / Bhango, Zibusiso; van der Haar, Dustin.
Business Information Systems - 22nd International Conference, BIS 2019, Proceedings. ed. / Witold Abramowicz; Rafael Corchuelo. Springer Verlag, 2019. p. 259-270 (Lecture Notes in Business Information Processing; Vol. 353).

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

TY - GEN

T1 - A Model for Inebriation Recognition in Humans Using Computer Vision

AU - Bhango, Zibusiso

AU - van der Haar, Dustin

PY - 2019

Y1 - 2019

N2 - The cost of substance use regarding lives lost, medical and psychiatric morbidity and social disruptions by far surpasses the economic costs. Alcohol abuse and dependence has been a social issue in need of addressing for centuries now. Methods exist that attempt to solve this problem by recognizing inebriation in humans. These methods include the use of blood tests, breathalyzers, urine tests, ECGs and wearables devices. Although effective, these methods are very inconvenient for the user, and the required equipment is expensive. We propose a method that provides a faster and convenient way to recognize inebriation. Our method uses Viola-Jones-based face-detection for the region of interest. The face images become input to a Convolutional Neural Network (CNN) which attempts to classify inebriation. In order to test our model’s performance against other methods, we implemented Local Binary Patterns (LBP) for feature extraction, and Support Vector Machines (SVM), Gaussian Naive Bayes (GNB) and k-Nearest Neighbor (kNN) classifiers. Our model had an accuracy rate of 84.31% and easily outperformed the other methods.

AB - The cost of substance use regarding lives lost, medical and psychiatric morbidity and social disruptions by far surpasses the economic costs. Alcohol abuse and dependence has been a social issue in need of addressing for centuries now. Methods exist that attempt to solve this problem by recognizing inebriation in humans. These methods include the use of blood tests, breathalyzers, urine tests, ECGs and wearables devices. Although effective, these methods are very inconvenient for the user, and the required equipment is expensive. We propose a method that provides a faster and convenient way to recognize inebriation. Our method uses Viola-Jones-based face-detection for the region of interest. The face images become input to a Convolutional Neural Network (CNN) which attempts to classify inebriation. In order to test our model’s performance against other methods, we implemented Local Binary Patterns (LBP) for feature extraction, and Support Vector Machines (SVM), Gaussian Naive Bayes (GNB) and k-Nearest Neighbor (kNN) classifiers. Our model had an accuracy rate of 84.31% and easily outperformed the other methods.

KW - Computer vision

KW - Convolutional Neural Networks

KW - Inebriation recognition

KW - k-Nearest Neighbor

KW - Machine learning

KW - Naive Bayes

KW - Support Vector Machines

UR - https://www.scopus.com/pages/publications/85068118271

U2 - 10.1007/978-3-030-20485-3_20

DO - 10.1007/978-3-030-20485-3_20

M3 - Conference contribution

AN - SCOPUS:85068118271

SN - 9783030204846

T3 - Lecture Notes in Business Information Processing

SP - 259

EP - 270

BT - Business Information Systems - 22nd International Conference, BIS 2019, Proceedings

A2 - Abramowicz, Witold

A2 - Corchuelo, Rafael

PB - Springer Verlag

T2 - 22nd International Conference on Business Information Systems, BIS 2019

Y2 - 26 June 2019 through 28 June 2019

ER -

A Model for Inebriation Recognition in Humans Using Computer Vision

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this