A5011019501- Biometric Identification and Security
- Face recognition and analysis
- Retinal Imaging and Analysis
- Glaucoma and retinal disorders
- Privacy-Preserving Technologies in Data
- Face and Expression Recognition
- Ocular Disorders and Treatments
- Adversarial Robustness in Machine Learning
- Gait Recognition and Analysis
- Generative Adversarial Networks and Image Synthesis
- Retinal and Optic Conditions
- Music and Audio Processing
- Anomaly Detection Techniques and Applications
- Arts, Culture, and Music Studies
- Time Series Analysis and Forecasting
- Software Engineering and Design Patterns
- Digital Media Forensic Detection
- Service-Oriented Architecture and Web Services
- Facial Nerve Paralysis Treatment and Research
- Web Application Security Vulnerabilities
- Vehicle License Plate Recognition
- User Authentication and Security Systems
University of Ljubljana
2017-2024
Biometric recognition technology has made significant advances over the last decade and is now used across a number of services applications. However, this widespread deployment also resulted in privacy concerns evolving societal expectations about appropriate use technology. For example, ability to automatically extract age, gender, race, health cues from biometric data heightened leakage. Face technology, particular, been spotlight, seen by many as posing considerable risk personal...
Segmentation techniques for ocular biometrics typically focus on finding a single eye region in the input image at time. Only limited work has been done multi-class segmentation despite number of obvious advantages. In this paper we address gap and present deep model build around SegNet architecture. We train small dataset (of 120 samples) images observe it to generalize well unseen ensure highly accurate results. evaluate Multi-Angle Sclera Database (MASD) describe comprehensive experiments...
Convolutional Neural Networks (CNNs) are today the de-facto standard for extracting compact and discriminative face representations (templates) from images in automatic recognition systems. Due to characteristics of CNN models, generated typically encode a multitude information ranging identity soft-biometric attributes, such as age, gender or ethnicity. However, since these were computed purpose only, contained templates represents serious privacy risk. To mitigate this problem, we present...
This paper summarises the results of Sclera Segmentation and Eye Recognition Benchmarking Competition (SSERBC 2017). It was organised in context International Joint Conference on Biometrics (IJCB The aim this competition to record recent developments sclera segmentation eye recognition visible spectrum (using iris, peri-ocular, their fusion), also gain attention researchers subject. In regard, we have used Multi-Angle Dataset (MASD version 1). is comprised of2624 images taken from both eyes...
Research on soft-biometrics showed that privacy-sensitive information can be deduced from biometric data. Utilizing templates only, about a persons gender, age, ethnicity, sexual orientation, and health state deduced. For many applications, these are expected to used for recognition purposes only. Thus, extracting this raises major privacy issues. Previous work proposed two kinds of learning-based solutions problem. The first ones provide strong privacy-enhancements, but limited pre-defined...
This paper summarises the results of Sclera Segmentation Benchmarking Competition (SSBC 2018). It was organised in context 11th IAPR International Conference on Biometrics (ICB The aim this competition to record developments sclera segmentation cross-sensor environment (sclera trait captured using multiple acquiring sensors). Additionally, also aimed gain attention researchers subject research. For purpose benchmarking, we have developed two datasets images different sensors. first dataset...
Soft–biometric privacy–enhancing techniques represent machine learning methods that aim to: (i) mitigate privacy concerns associated with face recognition technology by suppressing selected soft–biometric attributes in facial images (e.g., gender, age, ethnicity) and (ii) make unsolicited extraction of sensitive personal information infeasible. Because such are increasingly used real–world applications, it is imperative to understand what extent the enhancement can be inverted how much...
The periocular region of a face can be used as an autonomous modality in biometric recognition system. We evaluate two different deep learning pipelines, one with specific segmentation step and without it, show the positive negative properties both them. obtained results on newly introduced public dataset SBVPI that offers enough distinguishing information for successful identity recognition.
Soft-biometric privacy enhancing techniques (SB-PETs) transform facial images to preserve identity while preventing the automatic extraction of soft-biometrics by confusing machines through noise injections or attribute obfuscation. However, existing SB-PETs often sacrifice image quality for enhancement, limiting practical usage, especially in applications that allow human inspection. To address these issues, we introduce a novel SB-PET (i) generates photo-realistic with obscured gender...
Soft-biometric privacy-enhancing techniques represent machine learning methods that aim to: (i) mitigate privacy concerns associated with face recognition technology by suppressing selected soft-biometric attributes in facial images (e.g., gender, age, ethnicity) and (ii) make unsolicited extraction of sensitive personal information infeasible. Because such are increasingly used real-world applications, it is imperative to understand what extent the enhancement can be inverted how much...
Prepoznava ljudi je temeljni problem, s katerim se ukvarja področje biometrije. V našem delu ukvarjamo prepoznavo beločničnih žilnih struktur, ki imajo številne prednosti pred ostalimi značilkami: beločnične žile so edinstvene, tudi med identičnimi dvojčki – celo bolj kot prstni odtisi; za zajem ne potrebujemo posebnih naprav, le običajen fotoaparat ali mobilno kamero; neinvaziven in omogoča na daljavo; žilne strukture bistveno spreminjajo tekom življenja; težko ponarediti. Ker biometrija,...
Prepoznava ljudi je temeljni problem, s katerim se ukvarja področje biometrije. V našem delu ukvarjamo prepoznavo beločničnih žilnih struktur, ki imajo številne prednosti pred ostalimi značilkami: beločnične žile so edinstvene, tudi med identičnimi dvojčki – celo bolj kot prstni odtisi; za zajem ne potrebujemo posebnih naprav, le običajen fotoaparat ali mobilno kamero; neinvaziven in omogoča na daljavo; žilne strukture bistveno spreminjajo tekom življenja; težko ponarediti. Ker biometrija,...