Face liveness detection using Dynamic Local Ternary Pattern (DLTP)

Face spoofing is considered to be one of the prominent threats to face recognition systems. However, in order to improve the security measures of such biometric systems against deliberate spoof attacks, liveness detection has received significant recent attention from researchers. For this purpose,...

Full description

Bibliographic Details
Main Authors: Parveen, Sajida, Syed Ahmad Abdul Rahman, Sharifah Mumtazah, Hasan Abbas, Nidaa, Wan Adnan, Wan Azizun, Hanafi, Marsyita, Naeem, Nadeem
Format: Article
Language:English
Published: MDPI 2016
Subjects:
Online Access:http://psasir.upm.edu.my/id/eprint/54262/
http://psasir.upm.edu.my/id/eprint/54262/1/Face%20liveness%20detection%20using%20Dynamic%20Local%20Ternary%20Pattern%20%28DLTP%29.pdf
_version_ 1848852497045651456
author Parveen, Sajida
Syed Ahmad Abdul Rahman, Sharifah Mumtazah
Hasan Abbas, Nidaa
Wan Adnan, Wan Azizun
Hanafi, Marsyita
Naeem, Nadeem
author_facet Parveen, Sajida
Syed Ahmad Abdul Rahman, Sharifah Mumtazah
Hasan Abbas, Nidaa
Wan Adnan, Wan Azizun
Hanafi, Marsyita
Naeem, Nadeem
author_sort Parveen, Sajida
building UPM Institutional Repository
collection Online Access
description Face spoofing is considered to be one of the prominent threats to face recognition systems. However, in order to improve the security measures of such biometric systems against deliberate spoof attacks, liveness detection has received significant recent attention from researchers. For this purpose, analysis of facial skin texture properties becomes more popular because of its limited resource requirement and lower processing cost. The traditional method of skin analysis for liveness detection was to use Local Binary Pattern (LBP) and its variants. LBP descriptors are effective, but they may exhibit certain limitations in near uniform patterns. Thus, in this paper, we demonstrate the effectiveness of Local Ternary Pattern (LTP) as an alternative to LBP. In addition, we adopted Dynamic Local Ternary Pattern (DLTP), which eliminates the manual threshold setting in LTP by using Weber’s law. The proposed method was tested rigorously on four facial spoof databases: three are public domain databases and the other is the Universiti Putra Malaysia (UPM) face spoof database, which was compiled through this study. The results obtained from the proposed DLTP texture descriptor attained optimum accuracy and clearly outperformed the reported LBP and LTP texture descriptors.
first_indexed 2025-11-15T10:39:01Z
format Article
id upm-54262
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T10:39:01Z
publishDate 2016
publisher MDPI
recordtype eprints
repository_type Digital Repository
spelling upm-542622018-03-09T02:51:14Z http://psasir.upm.edu.my/id/eprint/54262/ Face liveness detection using Dynamic Local Ternary Pattern (DLTP) Parveen, Sajida Syed Ahmad Abdul Rahman, Sharifah Mumtazah Hasan Abbas, Nidaa Wan Adnan, Wan Azizun Hanafi, Marsyita Naeem, Nadeem Face spoofing is considered to be one of the prominent threats to face recognition systems. However, in order to improve the security measures of such biometric systems against deliberate spoof attacks, liveness detection has received significant recent attention from researchers. For this purpose, analysis of facial skin texture properties becomes more popular because of its limited resource requirement and lower processing cost. The traditional method of skin analysis for liveness detection was to use Local Binary Pattern (LBP) and its variants. LBP descriptors are effective, but they may exhibit certain limitations in near uniform patterns. Thus, in this paper, we demonstrate the effectiveness of Local Ternary Pattern (LTP) as an alternative to LBP. In addition, we adopted Dynamic Local Ternary Pattern (DLTP), which eliminates the manual threshold setting in LTP by using Weber’s law. The proposed method was tested rigorously on four facial spoof databases: three are public domain databases and the other is the Universiti Putra Malaysia (UPM) face spoof database, which was compiled through this study. The results obtained from the proposed DLTP texture descriptor attained optimum accuracy and clearly outperformed the reported LBP and LTP texture descriptors. MDPI 2016 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/54262/1/Face%20liveness%20detection%20using%20Dynamic%20Local%20Ternary%20Pattern%20%28DLTP%29.pdf Parveen, Sajida and Syed Ahmad Abdul Rahman, Sharifah Mumtazah and Hasan Abbas, Nidaa and Wan Adnan, Wan Azizun and Hanafi, Marsyita and Naeem, Nadeem (2016) Face liveness detection using Dynamic Local Ternary Pattern (DLTP). Computers, 5 (2). pp. 1-15. ISSN 2073-431X http://www.mdpi.com/2073-431X/5/2/10 Face liveness detection; Dynamic local ternary pattern (DLTP); Skin texture analysis 10.3390/computers5020010
spellingShingle Face liveness detection; Dynamic local ternary pattern (DLTP); Skin texture analysis
Parveen, Sajida
Syed Ahmad Abdul Rahman, Sharifah Mumtazah
Hasan Abbas, Nidaa
Wan Adnan, Wan Azizun
Hanafi, Marsyita
Naeem, Nadeem
Face liveness detection using Dynamic Local Ternary Pattern (DLTP)
title Face liveness detection using Dynamic Local Ternary Pattern (DLTP)
title_full Face liveness detection using Dynamic Local Ternary Pattern (DLTP)
title_fullStr Face liveness detection using Dynamic Local Ternary Pattern (DLTP)
title_full_unstemmed Face liveness detection using Dynamic Local Ternary Pattern (DLTP)
title_short Face liveness detection using Dynamic Local Ternary Pattern (DLTP)
title_sort face liveness detection using dynamic local ternary pattern (dltp)
topic Face liveness detection; Dynamic local ternary pattern (DLTP); Skin texture analysis
url http://psasir.upm.edu.my/id/eprint/54262/
http://psasir.upm.edu.my/id/eprint/54262/
http://psasir.upm.edu.my/id/eprint/54262/
http://psasir.upm.edu.my/id/eprint/54262/1/Face%20liveness%20detection%20using%20Dynamic%20Local%20Ternary%20Pattern%20%28DLTP%29.pdf