A5073391891- Biometric Identification and Security
- Face recognition and analysis
- Face and Expression Recognition
- User Authentication and Security Systems
- Digital Media Forensic Detection
- Advanced Image Processing Techniques
- Generative Adversarial Networks and Image Synthesis
- Advanced Steganography and Watermarking Techniques
- Video Surveillance and Tracking Methods
- Facial Nerve Paralysis Treatment and Research
- Image Processing Techniques and Applications
- Advanced Vision and Imaging
- Handwritten Text Recognition Techniques
- Anomaly Detection Techniques and Applications
- Forensic and Genetic Research
- Forensic Fingerprint Detection Methods
- Image and Signal Denoising Methods
- Remote-Sensing Image Classification
- Speech and Audio Processing
- Image Enhancement Techniques
- Adversarial Robustness in Machine Learning
- Music and Audio Processing
- Advanced Image Fusion Techniques
- Spectroscopy and Chemometric Analyses
- Image Processing and 3D Reconstruction
Norwegian University of Science and Technology
2016-2025
Jain University
2024
Advanced Micro Devices (Canada)
2024
NTNU Samfunnsforskning
2016-2023
Zimmer Biomet (United States)
2023
Rangaraya Medical College
2023
Centre de Recerca Matemàtica
2021
Computer Vision Center
2021
Infosys (India)
2021
Escuela Superior Politecnica del Litoral
2020
Face biometrics is widely used in various applications including border control and facilitating the verification of travellers' identity claim with respect to his electronic passport (ePass). As most countries, passports are issued a citizen based on submitted photo which allows applicant provide morphed face conceal during application process. In this work, we propose novel approach leveraging transferable features from pre-trained Deep Convolutional Neural Networks (D-CNN) detect both...
The vulnerability of face recognition systems is a growing concern that has drawn the interest from both academic and research communities. Despite availability broad range presentation attack detection (PAD) (or countermeasure or antispoofing) schemes, there exists no superior PAD technique due to evolution sophisticated attacks spoof attacks). In this paper, we present new perspective for by introducing light field camera (LFC). Since use LFC can record direction each incoming ray in...
Widespread deployment of Automatic Border Control (ABC) along with the electronic Machine Readable Travel Documents (eMRTD) for person verification has enabled a prominent use case face biometrics in border control applications. Many countries issue eMRTD passports on basis printed biometric photo submitted by applicant. Some offer web-portals passport renewal, where citizens can upload their photo. These applications allow possibility being altered to beautify appearance data subject or...
With advancements in technology, it is now possible to create representations of human faces a seamless manner for fake media, leveraging the large-scale availability videos. These can be used conduct personation attacks on targeted subjects. Availability open source software and variety commercial applications provides an opportunity generate videos particular target subject number ways. In this article, we evaluate generalizability face detection methods through series studies benchmark...
With the widespread deployment of biometric recognition systems, interest in attacking these systems is increasing. One easiest ways to circumvent a system are so-called presentation attacks, which artefacts presented sensor either impersonate another subject or avoid being recognised. In recent past, vulnerabilities morphing attacks have been unveiled. such samples multiple subjects merged signal feature domain, order allow successful verification all contributing against morphed identity....
Morphed face images are artificially generated images, which blend the facial of two or more different data subjects into one. The resulting morphed image resembles constituent faces, both in visual and feature representation. If a is enroled as probe biometric system, contributing to will be verified against probe. As result this infiltration, referred attack, unambiguous assignment not warranted, i.e. unique link between subject annulled. In work, we investigate vulnerability systems such...
Vulnerability of iris recognition systems remains a challenge due to diverse presentation attacks that fail assure the reliability when adopting these in real-life scenarios. In this paper, we present an in-depth analysis on especially focusing photo print and electronic display (or screen) attack. To extent, introduce new relatively large scale visible spectrum artefact database comprised 3300 normal samples are captured by simulating five different system. We also propose novel attack...
The Face Recognition System (FRS) is known to be vulnerable the attacks using morphed face. As use of face characteristics are mandatory in electronic passport (ePass), morphing have raised potential concerns border security. In this paper, we analyze vulnerability FRS new attack performed averaged generated by simple pixel level averaging two images corresponding different subjects. We benchmark commercial both conventional and based attacks. further propose a novel algorithm on...
Face recognition has been successfully deployed in real-time applications, including secure applications such as border control. The vulnerability of face systems (FRSs) to various kinds attacks (both direct and indirect attacks) morphing received great interest from the biometric community. goal a attack is subvert an FRS at automatic control (ABC) gate by presenting electronic machine-readable travel document (eMRTD) or e-passport that obtained based on morphed image. Since application...
The primary objective of face morphing is to com-bine images different data subjects (e.g. an malicious actor and accomplice) generate a image that can be equally verified for both contributing subjects. In this paper, we propose new framework generating morphs using newer Generative Adversarial Network (GAN) - StyleGAN. contrast earlier works, realistic high-quality high resolution 1024 × pixels. With the newly created dataset 2500 morphed images, pose critical question in work. (i) Can GAN...
Face morphing attacks target to circumvent Recognition Systems (FRS) by employing face images derived from multiple data subjects (e.g., accomplices and malicious actors). Morphed can be verified against contributing with a reasonable success rate, given they have high degree of facial resemblance. The is directly dependent on the quality generated morph images. We present new approach for generating strong extending our earlier framework morphs. using an Identity Prior Driven Generative...
Morphing attacks have posed a severe threat to Face Recognition System (FRS). Despite the number of advancements reported in recent works, we note serious open issues such as independent benchmarking, generalizability challenges and considerations age, gender, ethnicity that are inadequately addressed. Attack Detection (MAD) algorithms often prone generalization they database dependent. The existing databases, mostly semi-public nature, lack diversity terms ethnicity, various morphing...
This work reviews the results of NTIRE 2021 Challenge on Non-Homogeneous Dehazing. The proposed techniques and their have been evaluated a novel dataset that extends NH-Haze datset. It consists additional 35 pairs real haze free nonhomogeneous hazy images recorded outdoor. has introduced in outdoor scenes by using professional setup imitates conditions scenes. 327 participants registered challenge 23 teams competed final testing phase. solutions gauge state-of-the-art image dehazing.
This paper reviews the NTIRE 2023 challenge on image super-resolution (×4), focusing proposed solutions and results. The task of (SR) is to generate a high-resolution (HR) output from corresponding low-resolution (LR) input by leveraging prior information paired LR-HR images. aim obtain network design/solution capable produce high-quality results with best performance (e.g., PSNR). We want explore how high we can achieve regardless computational cost model size FLOPs) data. track was measure...
Secure authentication for smartphones is becoming important many applications such as financial transactions. Until today PIN and password are the most commonly used methods smartphone access control. Specifically a limited length passwords, level of security low thus can be compromised easily. In this work, we propose multi-modal biometric system, which uses face, periocular iris characteristics authentication. The proposed system tested on two different devices - Samsung Galaxy S5 Note...
This paper presents a novel method for global anomaly detection in crowded scenes. The proposed introduces the Particle Swarm Optimization (PSO) as robust algorithm optimizing interaction force computed using Social Force Model (SFM). main objective of is to drift population particles towards areas image motion. Such displacement driven by PSO fitness function aimed at minimizing force, so model most diffused and typical crowd behavior. Experiments are extensively conducted on public...
The vulnerability of finger vein recognition to spoofing attacks has emerged as a crucial security problem in the recent years mainly due high applications where biometric technology is used. Recent works shown that biometrics vulnerable attacks, pointing out importance investigate counter-measures against this type fraudulent actions. goal 1st Competition on Counter Measures Finger Vein Spoofing Attacks challenge researchers create can detect printed effectively. submitted approaches are...
Contact lens detection in the eye is a significant task to improve reliability of iris recognition systems. A contact overlays region and prevents sensor from capturing normal region. In this paper, we present novel scheme for detecting using Deep Convolutional Neural Network (CNN). The proposed CNN architecture ContlensNet structured have fifteen layers configured three-class problem with following classes: images textured (or colored) lens, soft transparent) no lens. trained numerous image...