Published on Thu Jun 24 2021

Differential Morph Face Detection using Discriminative Wavelet Sub-bands

Baaria Chaudhary, Poorya Aghdaie, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi

Face recognition systems are extremely vulnerable to morphing attacks. We propose a morph attack detection algorithm that leverages an undecimated 2D Discrete Wavelet Transform (DWT) for identifying morphed images.

8
0
0
Abstract

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.

Wed Jun 16 2021
Computer Vision
Detection of Morphed Face Images Using Discriminative Wavelet Sub-bands
This work investigates the well-known problem of morphing attacks. Morphed images have exposed face recognition systems' susceptibility to false acceptance. We show that a Deep Neural Network (DNN) trained on the 22 discriminative sub-bands can detect morphed samples precisely.
2
0
0
Wed Dec 02 2020
Computer Vision
Differential Morphed Face Detection Using Deep Siamese Networks
A successful morphing attack allows two or more people to use the same passport to cross borders. This is the first research work that makes use of a Siamese network architecture for morph attack detection.
0
0
0
Tue Jan 21 2020
Machine Learning
HRFA: High-Resolution Feature-based Attack
Adversarial attacks have long been developed for revealing the vulnerability of Deep Neural Networks. Most methods generate perturbations like normal noise, which is not interpretable and without semantic meaning. HRFA exerts attack by modifying the latent feature representation of the image.
0
0
0
Tue Jun 29 2021
Computer Vision
Attention Aware Wavelet-based Detection of Morphed Face Images
Morphed images have exploited loopholes in the face recognition checkpoints. We propose a wavelet-based morph detection methodology which adopts an end-to-end trainable soft attention mechanism. Our attention-based deep neural network (DNN)ocuses on the salient Regions of Interest (ROI)
4
0
0
Sat Mar 27 2021
Computer Vision
Going Deeper Into Face Detection: A Survey
0
0
0
Thu Jan 03 2019
Computer Vision
Face Recognition: A Novel Multi-Level Taxonomy based Survey
Face recognition systems have attracted increasing attention in multiple application areas. This paper proposes a new multi-level face recognition taxonomy. The taxonomy may also guide researchers in the development of more efficient face recognition solutions.
0
0
0
Wed Jun 16 2021
Computer Vision
Detection of Morphed Face Images Using Discriminative Wavelet Sub-bands
This work investigates the well-known problem of morphing attacks. Morphed images have exposed face recognition systems' susceptibility to false acceptance. We show that a Deep Neural Network (DNN) trained on the 22 discriminative sub-bands can detect morphed samples precisely.
2
0
0
Fri Nov 28 2014
Computer Vision
Deep Learning Face Attributes in the Wild
Predicting face attributes in the wild is challenging due to complex face variations. We propose a novel deep learning framework for attribute prediction. It cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently.
0
0
0
Mon Oct 23 2017
Computer Vision
VGGFace2: A dataset for recognising faces across pose and age
The dataset contains 3.31 million images of 9131 subjects. Images are downloaded from Google Image Search. Images have large variations in pose, age, illumination, ethnicity and profession.
0
0
0
Tue Jul 07 2020
Computer Vision
Can GAN Generated Morphs Threaten Face Recognition Systems Equally as Landmark Based Morphs? -- Vulnerability and Detection
The primary objective of face morphing is to combine face images of different data subjects. We propose a new framework for generating face morphs using a newer Generative Adversarial Network (GAN) - StyleGAN. In contrast to earlier works, we generate realistic morphs of both high-
0
0
0
Wed Dec 02 2020
Computer Vision
Mutual Information Maximization on Disentangled Representations for Differential Morph Detection
In our framework, the face image is represented in the embedding domain using two disentangled but complementary representations. The network is trained by triplets of face images, in which the intermediate image inherits the landmarks from one image and the appearance from the other image.
0
0
0
Thu Jun 02 2016
Machine Learning
Adversarially Learned Inference
We introduce the adversarially learned inference (ALI) model. It jointly learns a generation network and an inference network using an adversarial process. We illustrate the ability of the model to learn mutually coherent inference and generation networks. We confirm the usefulness of the learned representations.
0
0
0