Mapping 2D to 3D forensic facial recognition via bio-inspired active appearance model

Siti Zaharah Abd Rahman, Siti Norul Huda Sheikh Abdullah, Lim Eng Hao, Mohammed Hasan Abdulameer, Nazri Ahmad Zamani, Mohammad Zaharudin A Darus

Research output: Contribution to journalArticle

Abstract

This research done is to solve the problems faced by digital forensic analysts in identifying a suspect captured on their CCTV. Identifying the suspect through the CCTV video footage is a very challenging task for them as it involves tedious rounds of processes to match the facial information in the video footage to a set of suspect’s images. The biggest problem faced by digital forensic analysis is modeling 2D model extracted from CCTV video as the model does not provide enough information to carry out the identification process. Problems occur when a suspect in the video is not facing the camera, the image extracted is the side image of the suspect and it is difficult to make a matching with portrait image in the database. There are also many factors that contribute to the process of extracting facial information from a video to be difficult, such as low-quality video. Through 2D to 3D image model mapping, any partial face information that is incomplete can be matched more efficiently with 3D data by rotating it to matched position. The first methodology in this research is data collection; any data obtained through video recorder. Then, the video will be converted into an image. Images are used to develop the Active Appearance Model (the 2D face model is AAM) 2D and AAM 3D. AAM is used as an input for learning and testing process involving three classifiers, which are Random Forest, Support Vector Machine (SVM), and Neural Networks classifier. The experimental results show that the 3D model is more suitable for use in face recognition as the percentage of the recognition is higher compared with the 2D model.

Original languageEnglish
Pages (from-to)121-129
Number of pages9
JournalJurnal Teknologi
Volume78
Issue number2-2
DOIs
Publication statusPublished - 2016

Fingerprint

Closed circuit television systems
Classifiers
Face recognition
Support vector machines
Cameras
Neural networks
Testing
Digital forensics

Keywords

  • AAM
  • Forensic facial recognition
  • Mapping

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Rahman, S. Z. A., Sheikh Abdullah, S. N. H., Hao, L. E., Abdulameer, M. H., Zamani, N. A., & Darus, M. Z. A. (2016). Mapping 2D to 3D forensic facial recognition via bio-inspired active appearance model. Jurnal Teknologi, 78(2-2), 121-129. https://doi.org/10.11113/jt.v78.6939

Mapping 2D to 3D forensic facial recognition via bio-inspired active appearance model. / Rahman, Siti Zaharah Abd; Sheikh Abdullah, Siti Norul Huda; Hao, Lim Eng; Abdulameer, Mohammed Hasan; Zamani, Nazri Ahmad; Darus, Mohammad Zaharudin A.

In: Jurnal Teknologi, Vol. 78, No. 2-2, 2016, p. 121-129.

Research output: Contribution to journalArticle

Rahman, Siti Zaharah Abd ; Sheikh Abdullah, Siti Norul Huda ; Hao, Lim Eng ; Abdulameer, Mohammed Hasan ; Zamani, Nazri Ahmad ; Darus, Mohammad Zaharudin A. / Mapping 2D to 3D forensic facial recognition via bio-inspired active appearance model. In: Jurnal Teknologi. 2016 ; Vol. 78, No. 2-2. pp. 121-129.
@article{6d3b193adf6d4caab254188417e52720,
title = "Mapping 2D to 3D forensic facial recognition via bio-inspired active appearance model",
abstract = "This research done is to solve the problems faced by digital forensic analysts in identifying a suspect captured on their CCTV. Identifying the suspect through the CCTV video footage is a very challenging task for them as it involves tedious rounds of processes to match the facial information in the video footage to a set of suspect’s images. The biggest problem faced by digital forensic analysis is modeling 2D model extracted from CCTV video as the model does not provide enough information to carry out the identification process. Problems occur when a suspect in the video is not facing the camera, the image extracted is the side image of the suspect and it is difficult to make a matching with portrait image in the database. There are also many factors that contribute to the process of extracting facial information from a video to be difficult, such as low-quality video. Through 2D to 3D image model mapping, any partial face information that is incomplete can be matched more efficiently with 3D data by rotating it to matched position. The first methodology in this research is data collection; any data obtained through video recorder. Then, the video will be converted into an image. Images are used to develop the Active Appearance Model (the 2D face model is AAM) 2D and AAM 3D. AAM is used as an input for learning and testing process involving three classifiers, which are Random Forest, Support Vector Machine (SVM), and Neural Networks classifier. The experimental results show that the 3D model is more suitable for use in face recognition as the percentage of the recognition is higher compared with the 2D model.",
keywords = "AAM, Forensic facial recognition, Mapping",
author = "Rahman, {Siti Zaharah Abd} and {Sheikh Abdullah}, {Siti Norul Huda} and Hao, {Lim Eng} and Abdulameer, {Mohammed Hasan} and Zamani, {Nazri Ahmad} and Darus, {Mohammad Zaharudin A}",
year = "2016",
doi = "10.11113/jt.v78.6939",
language = "English",
volume = "78",
pages = "121--129",
journal = "Jurnal Teknologi",
issn = "0127-9696",
publisher = "Penerbit Universiti Teknologi Malaysia",
number = "2-2",

}

TY - JOUR

T1 - Mapping 2D to 3D forensic facial recognition via bio-inspired active appearance model

AU - Rahman, Siti Zaharah Abd

AU - Sheikh Abdullah, Siti Norul Huda

AU - Hao, Lim Eng

AU - Abdulameer, Mohammed Hasan

AU - Zamani, Nazri Ahmad

AU - Darus, Mohammad Zaharudin A

PY - 2016

Y1 - 2016

N2 - This research done is to solve the problems faced by digital forensic analysts in identifying a suspect captured on their CCTV. Identifying the suspect through the CCTV video footage is a very challenging task for them as it involves tedious rounds of processes to match the facial information in the video footage to a set of suspect’s images. The biggest problem faced by digital forensic analysis is modeling 2D model extracted from CCTV video as the model does not provide enough information to carry out the identification process. Problems occur when a suspect in the video is not facing the camera, the image extracted is the side image of the suspect and it is difficult to make a matching with portrait image in the database. There are also many factors that contribute to the process of extracting facial information from a video to be difficult, such as low-quality video. Through 2D to 3D image model mapping, any partial face information that is incomplete can be matched more efficiently with 3D data by rotating it to matched position. The first methodology in this research is data collection; any data obtained through video recorder. Then, the video will be converted into an image. Images are used to develop the Active Appearance Model (the 2D face model is AAM) 2D and AAM 3D. AAM is used as an input for learning and testing process involving three classifiers, which are Random Forest, Support Vector Machine (SVM), and Neural Networks classifier. The experimental results show that the 3D model is more suitable for use in face recognition as the percentage of the recognition is higher compared with the 2D model.

AB - This research done is to solve the problems faced by digital forensic analysts in identifying a suspect captured on their CCTV. Identifying the suspect through the CCTV video footage is a very challenging task for them as it involves tedious rounds of processes to match the facial information in the video footage to a set of suspect’s images. The biggest problem faced by digital forensic analysis is modeling 2D model extracted from CCTV video as the model does not provide enough information to carry out the identification process. Problems occur when a suspect in the video is not facing the camera, the image extracted is the side image of the suspect and it is difficult to make a matching with portrait image in the database. There are also many factors that contribute to the process of extracting facial information from a video to be difficult, such as low-quality video. Through 2D to 3D image model mapping, any partial face information that is incomplete can be matched more efficiently with 3D data by rotating it to matched position. The first methodology in this research is data collection; any data obtained through video recorder. Then, the video will be converted into an image. Images are used to develop the Active Appearance Model (the 2D face model is AAM) 2D and AAM 3D. AAM is used as an input for learning and testing process involving three classifiers, which are Random Forest, Support Vector Machine (SVM), and Neural Networks classifier. The experimental results show that the 3D model is more suitable for use in face recognition as the percentage of the recognition is higher compared with the 2D model.

KW - AAM

KW - Forensic facial recognition

KW - Mapping

UR - http://www.scopus.com/inward/record.url?scp=84960077686&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960077686&partnerID=8YFLogxK

U2 - 10.11113/jt.v78.6939

DO - 10.11113/jt.v78.6939

M3 - Article

VL - 78

SP - 121

EP - 129

JO - Jurnal Teknologi

JF - Jurnal Teknologi

SN - 0127-9696

IS - 2-2

ER -