Morphing Detection Using a General- Purpose Face Recognition System

Abstract

Image morphing has proven to be very successful at deceiving facial recognition systems. Such a vulnerability can be critical when exploited in an automatic border control scenario. Recent works on this topic rely on dedicated algorithms which require additional software modules deployed alongside an existing facial recognition system. In this work, we address the problem of morphing detection by using state-of-the-art facial recognition algorithms based on hand-crafted features and deep convolutional neural networks. We show that a general-purpose face recognition system combined with a simple linear classifier can be successfully used as a morphing detector. The proposed method reuses an existing feature extraction pipeline instead of introducing additional modules. It requires neither fine-tuning nor modifications to the existing recognition system and can be trained using only a small dataset. The proposed approach achieves state-of-the-art performance on our morphing datasets using a 5-fold cross-validation.

Border Control Morphing Attack Detection with a Convolutional Neural Network De-morphing Approach

“…From a substantive viewpoint, morphing's corpora are designed with open source and well-known software such as the GNU Image Manipulation Program (GIMP) which has a plugin called the GIMP Animation Package (GAP) [26]. This plugin is able to merge images [10], [13], [23], [27], but most of the software uses the Delaunay-Voronoi triangulation algorithm (DVT) [28]- [33] and a swapping technique to improve the outcome achieved [34]- [39]. Moreover, some current research works use morphing pictures with generative adversarial networks (GANs) instead of using the triangulation process as mentioned previously [25].…”

“…On the one hand, there are research works that rely on micro-textures which use some features such as the local binary pattern (LBP - [40]) in [25], [31], [39], [41]- [43], or weighted local magnitude pattern (WLMP) which is proposed and explained in [44]. On the other hand, there are research works based on analysis of descriptors which use the scale invariant feature transform (SIFT - [45]) in [46], binarized statistical image features (BSIF - [47]) in [27], and speeded-up robust features (SURF - [48]) in [34].…”

“…With the advent of deep learning in the last decades, some approaches use convolutional neural networks (CNNs) to detect the morphing process [25], [38], [39], [51]. Some of the most well-known corpora are VGG19 [52], AlexNet [53] or GAN [54], [55].…”

Computer Science & Information Technology (CS & IT)

“…Existing face recognition systems have also been used to detect morphs. In [11], the highlevel features of existing, deep-learning-based FRSs are used to train a Support Vector Machine (SVM) [12]. The resulting hyperplane is used to classify images as morphs or genuine photos.…”

“…However, such a threshold would not be useful in practice since too many genuine claims would be rejected. Since there is often a trade-off between the performance of face verification and morphing detection [11], we display our results by plotting EER against MAR EER . The Relative Morph Match Rate (RMMR) [16] attempts to describe something similar, but this value is rarely reported.…”