Towards minimizing efforts for Morphing Attacks-Deep embeddings for morphing pair selection and improved Morphing Attack Detection.

Face Morphing Attacks pose a threat to the security of identity documents, especially with respect to a subsequent access control process, because they allow both involved individuals to use the same document. Several algorithms are currently being developed to detect Morphing Attacks, often requiring large data sets of morphed face images for training. In the present study, face embeddings are used for two different purposes: first, to pre-select images for the subsequent large-scale generation of Morphing Attacks, and second, to detect potential Morphing Attacks. Previous studies have demonstrated the power of embeddings in both use cases. However, we aim to build on these studies by adding the more powerful MagFace model to both use cases, and by performing comprehensive analyses of the role of embeddings in pre-selection and attack detection in terms of the vulnerability of face recognition systems and attack detection algorithms. In particular, we use recent developments to assess the attack potential, but also investigate the influence of morphing algorithms. For the first objective, an algorithm is developed that pairs individuals based on the similarity of their face embeddings. Different state-of-the-art face recognition systems are used to extract embeddings in order to pre-select the face images and different morphing algorithms are used to fuse the face images. The attack potential of the differently generated morphed face images will be quantified to compare the usability of the embeddings for automatically generating a large number of successful Morphing Attacks. For the second objective, we compare the performance of the embeddings of two state-of-the-art face recognition systems with respect to their ability to detect morphed face images. Our results demonstrate that ArcFace and MagFace provide valuable face embeddings for image pre-selection. Various open-source and commercial-off-the-shelf face recognition systems are vulnerable to the generated Morphing Attacks, and their vulnerability increases when image pre-selection is based on embeddings compared to random pairing. In particular, landmark-based closed-source morphing algorithms generate attacks that pose a high risk to any tested face recognition system. Remarkably, more accurate face recognition systems show a higher vulnerability to Morphing Attacks. Among the systems tested, commercial-off-the-shelf systems were the most vulnerable to Morphing Attacks. In addition, MagFace embeddings stand out as a robust alternative for detecting morphed face images compared to the previously used ArcFace embeddings. The results endorse the benefits of face embeddings for more effective image pre-selection for face morphing and for more accurate detection of morphed face images, as demonstrated by extensive analysis of various designed attacks. The MagFace model is a powerful alternative to the often-used ArcFace model in detecting attacks and can increase performance depending on the use case. It also highlights the usability of embeddings to generate large-scale morphed face databases for various purposes, such as training Morphing Attack Detection algorithms as a countermeasure against attacks.

Parameter-Free Matrix Decomposition for Specular Reflections Removal in Endoscopic Images.

Objective: Endoscopy is a medical diagnostic procedure used to see inside the human body with the help of a camera-attached system called the endoscope. Endoscopic images and videos suffer from specular reflections (or highlight) and can have an adverse impact on the diagnostic quality of images. These scattered white regions severely affect the visual appearance of images for both endoscopists and the computer-aided diagnosis of diseases. Methods & Results: We introduce a new parameter-free matrix decomposition technique to remove the specular reflections. The proposed method decomposes the original image into a highlight-free pseudo-low-rank component and a highlight component. Along with the highlight removal, the approach also removes the boundary artifacts present around the highlight regions, unlike the previous works based on family of Robust Principal Component Analysis (RPCA). The approach is evaluated on three publicly available endoscopy datasets: Kvasir Polyp, Kvasir Normal-Pylorus and Kvasir Capsule datasets. Our evaluation is benchmarked against 4 different state-of-the-art approaches using three different well-used metrics such as Structural Similarity Index Measure (SSIM), Percentage of highlights remaining and Coefficient of Variation (CoV). Conclusions: The results show significant improvements over the compared methods on all three metrics. The approach is further validated for statistical significance where it emerges better than other state-of-the-art approaches.Clinical and Translational Impact Statement-The mathematical concepts of low rank and rank decomposition in matrix algebra are translated to remove specularities in the endoscopic images The result shows the impact of the proposed method in removing specular reflections from endoscopic images indicating improved diagnosis efficiency for both endoscopists and computer-aided diagnosis systems.

Template-Driven Knowledge Distillation for Compact and Accurate Periocular Biometrics Deep-Learning Models.

This work addresses the challenge of building an accurate and generalizable periocular recognition model with a small number of learnable parameters. Deeper (larger) models are typically more capable of learning complex information. For this reason, knowledge distillation (kd) was previously proposed to carry this knowledge from a large model (teacher) into a small model (student). Conventional KD optimizes the student output to be similar to the teacher output (commonly classification output). In biometrics, comparison (verification) and storage operations are conducted on biometric templates, extracted from pre-classification layers. In this work, we propose a novel template-driven KD approach that optimizes the distillation process so that the student model learns to produce templates similar to those produced by the teacher model. We demonstrate our approach on intra- and cross-device periocular verification. Our results demonstrate the superiority of our proposed approach over a network trained without KD and networks trained with conventional (vanilla) KD. For example, the targeted small model achieved an equal error rate (EER) value of 22.2% on cross-device verification without KD. The same model achieved an EER of 21.9% with the conventional KD, and only 14.7% EER when using our proposed template-driven KD.

Reverse Peroneal Artery Flap-A Workhorse Flap for Reconstruction of Large, Distal Defects of Ankle and Foot.

Background Reconstruction of large foot and ankle defects is a difficult task due to less available local soft tissue and more critical from functional point of view. To overcome the limitations associated with locoregional flaps and free flaps, reverse peroneal artery (RPA) flap was selected and its usefulness in reconstruction of distal large defects of the ankle and foot and its complications were studied. Materials and Methods This is a prospective observational study done in 20 patients treated as cohort within 2 years and 8 months from January 2018 to August 2020. Large defects of foot and ankle were reconstructed with RPA flap and evaluated for its usefulness. Three cases were evaluated with computed tomography angiography postoperatively, to assess the vascular pattern. Conclusion RPA flap is a versatile and very reliable flap for the reconstruction of large and distal defects of foot and ankle. It is safely done in children and in acute trauma without any major complications.

Direct Unsupervised Super-Resolution Using Generative Adversarial Network (DUS-GAN) for Real-World Data.

The deep learning models for the Single Image Super-Resolution (SISR) task have found success in recent years. However, one of the prime limitations of existing deep learning-based SISR approaches is that they need supervised training. Specifically, the Low-Resolution (LR) images are obtained through known degradation (for instance, bicubic downsampling) from the High-Resolution (HR) images to provide supervised data as an LR-HR pair. Such training results in a domain shift of learnt models when real-world data is provided with multiple degradation factors not present in the training set. To address this challenge, we propose an unsupervised approach for the SISR task using Generative Adversarial Network (GAN), which we refer to hereafter as DUS-GAN. The novel design of the proposed method accomplishes the SR task without degradation estimation of real-world LR data. In addition, a new human perception-based quality assessment loss, i.e., Mean Opinion Score (MOS), has also been introduced to boost the perceptual quality of SR results. The pertinence of the proposed method is validated with numerous experiments on different reference-based (i.e., NTIRE Real-world SR Challenge validation dataset) and no-reference based (i.e., NTIRE Real-world SR Challenge Track-1 and Track-2) testing datasets. The experimental analysis demonstrates committed improvement from the proposed method over the other state-of-the-art unsupervised SR approaches, both in terms of subjective and quantitative evaluations on different reference metrics (i.e., LPIPS, PI-RMSE graph) and no-reference quality measures such as NIQE, BRISQUE and PIQE. We also provide the implementation of the proposed approach (https://github.com/kalpeshjp89/DUSGAN) to support reproducible research.

Complexity and ultrastructure of infectious extracellular vesicles from cells infected by non-enveloped virus.

Enteroviruses support cell-to-cell viral transmission prior to their canonical lytic spread of virus. Poliovirus (PV), a prototype for human pathogenic positive-sense RNA enteroviruses, and picornaviruses in general, transport multiple virions en bloc via infectious extracellular vesicles, 100~1000 nm in diameter, secreted from host cells. Using biochemical and biophysical methods we identify multiple components in secreted microvesicles, including mature PV virions; positive-sense genomic and negative-sense replicative, template viral RNA; essential viral replication proteins; and cellular proteins. Using cryo-electron tomography, we visualize the near-native three-dimensional architecture of secreted infectious microvesicles containing both virions and a unique morphological component that we describe as a mat-like structure. While the composition of these mat-like structures is not yet known, based on our biochemical data they are expected to be comprised of unencapsidated RNA and proteins. In addition to infectious microvesicles, CD9-positive exosomes released from PV-infected cells are also infectious and transport virions. Thus, our data show that, prior to cell lysis, non-enveloped viruses are secreted within infectious vesicles that also transport viral unencapsidated RNAs, viral and host proteins. Understanding the structure and function of these infectious particles helps elucidate the mechanism by which extracellular vesicles contribute to the spread of non-enveloped virus infection.

Ultrasound Elastography is a Useful Adjunct to Conventional Ultrasonography and Needle Aspiration in Preoperative Prediction of Malignancy in Thyroid Nodules: A Northern India Perspective.

INTRODUCTION: Data on ultrasound elastography (USE) are scant from India. This study aimed to compare the sensitivity and specificity of USE with thyroid ultrasonography (USG) and fine-needle aspiration (FNA) as preoperative predictor of malignancy, using postoperative histopathology as gold standard. MATERIALS AND METHODS: Consecutive patients with thyroid swelling/goiter underwent thyroid USG followed by USE. Patients with pure cystic nodules or eggshell calcification were excluded. Patients with nodules >10 mm with one or more high-risk USG features underwent FNA. Patients with no USG high-risk features, benign score on USE, and benign FNA were conservatively followed. All other patients underwent thyroidectomy. RESULTS: 246 consecutive patients underwent USG. Data from 97 patients (117 nodules) were analyzed. Median age of patients was 43 years with 85.4% females. All patients with USE score-1 had benign USG and FNA characteristics. Of 86 nodules having USE score-2, 18.6% nodules were hypoechoic and 16.28% had microcalcification. Hypoechogenicity and microcalcifications were observed in 66.67% nodules with USE score-3. All nodules with USE score-4 and 5 were hypoechoic and had microcalcifications. Histopathology was benign in 84 and malignant in 33 patients. Occurrence of malignancy in USE scores 1-5 was 0, 4.65, 100, 90.5, and 100%, respectively. All eight nodules with diagnosis of follicular adenoma had preoperative USE score-2. The sensitivity of preoperative USG, USE, and FNA in picking up malignancy was 66.67, 87.88, and 69.70%, respectively. Specificity of USG, USE, and FNA in detecting thyroid malignancy was 88.10, 100, and 97.6%, respectively. False positivity rates for USG, USE, and FNA in diagnosing thyroid malignancy was 11.9, 0, and 2.4%, respectively. The overall diagnostic accuracy of USG, USE, and FNA cytology in this study was 82.05, 96.58, and 89.74%, respectively. CONCLUSION: USE may be better than USG for preoperative detection of malignancy in thyroid nodules.

Presentation attack detection for face recognition using light field camera.

The vulnerability of face recognition systems isa growing concern that has drawn the interest from both academic and research communities. Despite the availability of a broad range of face presentation attack detection (PAD)(or countermeasure or antispoofing) schemes, there exists no superior PAD technique due to evolution of sophisticated presentation attacks (or spoof attacks). In this paper, we present a new perspective for face presentation attack detection by introducing light field camera (LFC). Since the use of a LFC can record the direction of each incoming ray in addition to the intensity, it exhibits an unique characteristic of rendering multiple depth(or focus) images in a single capture. Thus, we present a novel approach that involves exploring the variation of the focus between multiple depth (or focus) images rendered by the LFC that in turn can be used to reveal the presentation attacks. To this extent, we first collect a new face artefact database using LFC that comprises of 80 subjects. Face artefacts are generated by simulating two widely used attacks, such as photo print and electronic screen attack. Extensive experiments carried out on the light field face artefact database have revealed the outstanding performance of the proposed PAD scheme when benchmarked with various well established state-of-the-art schemes.