skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Factor analysis in automated face detection: gender, occlusion, eyewear, brightness, contrast, and focus measure

Abstract

Computer-based facial recognition algorithms exploit the unique characteristics of faces in images. However, in non-cooperative situations these unique characteristics are often disturbed. In this study, we examine the effect of six different factors on face detection in an unconstrained imaging environment: image brightness, image contrast, focus measure, eyewear, gender, and occlusion. The aim of this study is twofold: first, to quantify detection rates of conventional Haar cascade algorithms across these six factors; and second, to propose methods for automatically labeling datasets whose size prohibits manual labeling. First, we manually classify a uniquely challenging dataset comprising 9,688 images of passengers in vehicles acquired from a roadside camera system. Next, we quantify how each of the aforementioned factors affect face detection on this dataset. Of the six factors studied, occlusion had the most significant impact, resulting in a 54% decrease in detection rate between unoccluded and severely occluded faces in our unique dataset. Finally, we provide a methodology for data analytics of large datasets where manual labeling of the whole dataset is not possible.

Authors:
 [1]; ORCiD logo [2];  [3];  [2]; ORCiD logo [2]; ORCiD logo [2]
  1. Brigham Young University
  2. ORNL
  3. The University of Tennessee, Knoxville
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1468194
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: SPIE Defense and Security - Orlando, Florida, United States of America - 4/15/2018 4:00:00 AM-4/19/2018 4:00:00 AM
Country of Publication:
United States
Language:
English

Citation Formats

Jafek, Benjamin, Eicholtz, Matthew R., Hendershot, John, Johnson, Christi R., Bolme, David S., and Santos-Villalobos, Hector J. Factor analysis in automated face detection: gender, occlusion, eyewear, brightness, contrast, and focus measure. United States: N. p., 2018. Web. doi:10.1117/12.2311281.
Jafek, Benjamin, Eicholtz, Matthew R., Hendershot, John, Johnson, Christi R., Bolme, David S., & Santos-Villalobos, Hector J. Factor analysis in automated face detection: gender, occlusion, eyewear, brightness, contrast, and focus measure. United States. doi:10.1117/12.2311281.
Jafek, Benjamin, Eicholtz, Matthew R., Hendershot, John, Johnson, Christi R., Bolme, David S., and Santos-Villalobos, Hector J. Tue . "Factor analysis in automated face detection: gender, occlusion, eyewear, brightness, contrast, and focus measure". United States. doi:10.1117/12.2311281. https://www.osti.gov/servlets/purl/1468194.
@article{osti_1468194,
title = {Factor analysis in automated face detection: gender, occlusion, eyewear, brightness, contrast, and focus measure},
author = {Jafek, Benjamin and Eicholtz, Matthew R. and Hendershot, John and Johnson, Christi R. and Bolme, David S. and Santos-Villalobos, Hector J.},
abstractNote = {Computer-based facial recognition algorithms exploit the unique characteristics of faces in images. However, in non-cooperative situations these unique characteristics are often disturbed. In this study, we examine the effect of six different factors on face detection in an unconstrained imaging environment: image brightness, image contrast, focus measure, eyewear, gender, and occlusion. The aim of this study is twofold: first, to quantify detection rates of conventional Haar cascade algorithms across these six factors; and second, to propose methods for automatically labeling datasets whose size prohibits manual labeling. First, we manually classify a uniquely challenging dataset comprising 9,688 images of passengers in vehicles acquired from a roadside camera system. Next, we quantify how each of the aforementioned factors affect face detection on this dataset. Of the six factors studied, occlusion had the most significant impact, resulting in a 54% decrease in detection rate between unoccluded and severely occluded faces in our unique dataset. Finally, we provide a methodology for data analytics of large datasets where manual labeling of the whole dataset is not possible.},
doi = {10.1117/12.2311281},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2018},
month = {5}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: