Influence of Image Enhancement Techniques on Effectiveness of Unconstrained Face Detection and Identification
In a criminal investigation, along with processing forensic evidence, different investigative techniques are used to identify the perpetrator of the crime. It includes collecting and analyzing unconstrained face images, mostly with low resolution and various qualities, making identification difficul...
Guardado en:
Autores principales: | , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Kaunas University of Technology
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/7dd839269dde411e9070fe3e2513ccf7 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:7dd839269dde411e9070fe3e2513ccf7 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:7dd839269dde411e9070fe3e2513ccf72021-11-04T14:25:05ZInfluence of Image Enhancement Techniques on Effectiveness of Unconstrained Face Detection and Identification10.5755/j02.eie.290811392-12152029-5731https://doaj.org/article/7dd839269dde411e9070fe3e2513ccf72021-10-01T00:00:00Zhttps://eejournal.ktu.lt/index.php/elt/article/view/29081https://doaj.org/toc/1392-1215https://doaj.org/toc/2029-5731In a criminal investigation, along with processing forensic evidence, different investigative techniques are used to identify the perpetrator of the crime. It includes collecting and analyzing unconstrained face images, mostly with low resolution and various qualities, making identification difficult. Since police organizations have limited resources, in this paper, we propose a novel method that utilizes off-the-shelf solutions (Dlib library Histogram of Oriented Gradients-HOG face detectors and the ResNet faces feature vector extractor) to provide practical assistance in unconstrained face identification. Our experiment aimed to establish which one (if any) of the basic image enhancement techniques should be applied to increase the effectiveness. Results obtained from three publicly available databases and one created for this research (simulating police investigators’ database) showed that resizing the image (especially with a resolution lower than 150 pixels) should always precede enhancement to improve face detection accuracy. The best results in determining whether they are the same or different persons in images were obtained by applying sharpening with a high-pass filter, whereas normalization gives the highest classification scores when a single weight value is applied to data from all four databases.Igor VukovicPetar CisarKristijan KukMilos BandjurBrankica PopovicKaunas University of Technologyarticleface detectionface recognitionhistogram of oriented gradientsimage processingElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENElektronika ir Elektrotechnika, Vol 27, Iss 5, Pp 49-58 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
face detection face recognition histogram of oriented gradients image processing Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
spellingShingle |
face detection face recognition histogram of oriented gradients image processing Electrical engineering. Electronics. Nuclear engineering TK1-9971 Igor Vukovic Petar Cisar Kristijan Kuk Milos Bandjur Brankica Popovic Influence of Image Enhancement Techniques on Effectiveness of Unconstrained Face Detection and Identification |
description |
In a criminal investigation, along with processing forensic evidence, different investigative techniques are used to identify the perpetrator of the crime. It includes collecting and analyzing unconstrained face images, mostly with low resolution and various qualities, making identification difficult. Since police organizations have limited resources, in this paper, we propose a novel method that utilizes off-the-shelf solutions (Dlib library Histogram of Oriented Gradients-HOG face detectors and the ResNet faces feature vector extractor) to provide practical assistance in unconstrained face identification. Our experiment aimed to establish which one (if any) of the basic image enhancement techniques should be applied to increase the effectiveness. Results obtained from three publicly available databases and one created for this research (simulating police investigators’ database) showed that resizing the image (especially with a resolution lower than 150 pixels) should always precede enhancement to improve face detection accuracy. The best results in determining whether they are the same or different persons in images were obtained by applying sharpening with a high-pass filter, whereas normalization gives the highest classification scores when a single weight value is applied to data from all four databases. |
format |
article |
author |
Igor Vukovic Petar Cisar Kristijan Kuk Milos Bandjur Brankica Popovic |
author_facet |
Igor Vukovic Petar Cisar Kristijan Kuk Milos Bandjur Brankica Popovic |
author_sort |
Igor Vukovic |
title |
Influence of Image Enhancement Techniques on Effectiveness of Unconstrained Face Detection and Identification |
title_short |
Influence of Image Enhancement Techniques on Effectiveness of Unconstrained Face Detection and Identification |
title_full |
Influence of Image Enhancement Techniques on Effectiveness of Unconstrained Face Detection and Identification |
title_fullStr |
Influence of Image Enhancement Techniques on Effectiveness of Unconstrained Face Detection and Identification |
title_full_unstemmed |
Influence of Image Enhancement Techniques on Effectiveness of Unconstrained Face Detection and Identification |
title_sort |
influence of image enhancement techniques on effectiveness of unconstrained face detection and identification |
publisher |
Kaunas University of Technology |
publishDate |
2021 |
url |
https://doaj.org/article/7dd839269dde411e9070fe3e2513ccf7 |
work_keys_str_mv |
AT igorvukovic influenceofimageenhancementtechniquesoneffectivenessofunconstrainedfacedetectionandidentification AT petarcisar influenceofimageenhancementtechniquesoneffectivenessofunconstrainedfacedetectionandidentification AT kristijankuk influenceofimageenhancementtechniquesoneffectivenessofunconstrainedfacedetectionandidentification AT milosbandjur influenceofimageenhancementtechniquesoneffectivenessofunconstrainedfacedetectionandidentification AT brankicapopovic influenceofimageenhancementtechniquesoneffectivenessofunconstrainedfacedetectionandidentification |
_version_ |
1718444848386670592 |