Differential Morph Face Detection using Discriminative Wavelet Sub-bands

被引:17
|
作者
Chaudhary, Baaria [1 ]
Aghdaie, Poorya [1 ]
Soleymani, Sobhan [1 ]
Dawson, Jeremy [1 ]
Nasrabadi, Nasser M. [1 ]
机构
[1] West Virginia Univ, Morgantown, WV 26506 USA
关键词
D O I
10.1109/CVPRW53098.2021.00158
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Face recognition systems are extremely vulnerable to morphing attacks, in which a morphed facial reference image can be successfully verified as two or more distinct identities. In this paper, we propose a morph attack detection algorithm that leverages an undecimated 2D Discrete Wavelet Transform (DWT) for identifying morphed face images. The core of our framework is that artifacts resulting from the morphing process that are not discernible in the image domain can be more easily identified in the spatial frequency domain. A discriminative wavelet sub-band can accentuate the disparity between a real and a morphed image. To this end, multi-level DWT is applied to all images, yielding 48 mid and high-frequency sub-bands each. The entropy distributions for each sub-band are calculated separately for both bona fide and morph images. For some of the sub-bands, there is a marked difference between the entropy of the sub-band in a bona fide image and the identical sub-band's entropy in a morphed image. Consequently, we employ Kullback-Liebler Divergence (KLD) to exploit these differences and isolate the sub-bands that are the most discriminative. We measure how discriminative a sub-band is by its KLD value and the 22 sub-bands with the highest KLD values are chosen for network training. Then, we train a deep Siamese neural network using these 22 selected sub-bands for differential morph attack detection. We examine the efficacy of discriminative wavelet sub-bands for morph attack detection and show that a deep neural network trained on these sub-bands can accurately identify morph imagery.
引用
收藏
页码:1425 / 1434
页数:10
相关论文
共 50 条
  • [1] Detection of Morphed Face Images Using Discriminative Wavelet Sub-bands
    Aghdaie, Poorya
    Chaudhary, Baaria
    Soleymani, Sobhan
    Dawson, Jeremy
    Nasrabadi, Nasser M.
    [J]. 2021 9TH INTERNATIONAL WORKSHOP ON BIOMETRICS AND FORENSICS (IWBF 2021), 2021,
  • [2] LBP BASED ON MULTI WAVELET SUB-BANDS FEATURE EXTRACTION USED FOR FACE RECOGNITION
    Rashid, Rasber D.
    Jassim, Sabah A.
    Sellahewa, Harin
    [J]. 2013 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2013,
  • [3] Classification of Brain MRI using the LH and HL Wavelet Transform Sub-bands
    Lahmiri, Salim
    Boukadoum, Mounir
    [J]. 2011 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2011, : 1025 - 1028
  • [4] Generative and Discriminative Modelling of Linear Energy Sub-bands for Spoof Detection in Speaker Verification Systems
    Suvidha Rupesh Kumar
    B. Bharathi
    [J]. Circuits, Systems, and Signal Processing, 2022, 41 : 3811 - 3831
  • [5] Lung Sound Classification Using Hjorth Descriptor Measurement on Wavelet Sub-bands
    Rizal, Achmad
    Hidayat, Risanuri
    Nugroho, Hanung Adi
    [J]. JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2019, 15 (05): : 1068 - 1081
  • [6] Generative and Discriminative Modelling of Linear Energy Sub-bands for Spoof Detection in Speaker Verification Systems
    Kumar, Suvidha Rupesh
    Bharathi, B.
    [J]. CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2022, 41 (07) : 3811 - 3831
  • [7] A Novel Ultrasound Image Enhancement Algorithm Using Cascaded Clustering on Wavelet Sub-bands
    Singh, Prerna
    Mukundan, Ramakrishnan
    De Ryke, Rex
    [J]. 2018 29TH IRISH SIGNALS AND SYSTEMS CONFERENCE (ISSC), 2018,
  • [8] An Image De-noising Method Using Directions of Wavelet Decomposition Sub-bands
    Cai, Zheng
    Tao, Shaohua
    [J]. MECHANICAL AND ELECTRONICS ENGINEERING III, PTS 1-5, 2012, 130-134 : 3058 - +
  • [9] Employing linear prediction residual signal of wavelet sub-bands in automatic detection of laryngeal pathology
    Akbari, Ali
    Arjmandi, Meisam Khalil
    [J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2015, 18 : 293 - 302
  • [10] RLC - BASED IMAGE COMPRESSION USING WAVELET DECOMPOSITION WITH ZERO - SETTING OF UNNECESSARY SUB-BANDS
    Dawood, Akram Abdul Mawjood
    Abdulaziz, Azhar Sabah
    Mohammed, Alnawar Jassim
    [J]. JOURNAL OF ENGINEERING SCIENCE AND TECHNOLOGY, 2022, 17 (01): : 391 - 403