A5071181711- Biometric Identification and Security
- Face recognition and analysis
- Neuroscience and Neural Engineering
- Cognitive Computing and Networks
- Video Surveillance and Tracking Methods
- User Authentication and Security Systems
- Face and Expression Recognition
- Muscle activation and electromyography studies
- Image Retrieval and Classification Techniques
- Muscle Physiology and Disorders
- Advanced Image and Video Retrieval Techniques
- Biomedical Text Mining and Ontologies
- Petri Nets in System Modeling
- Dermatoglyphics and Human Traits
- Advanced Vision and Imaging
- Parkinson's Disease Mechanisms and Treatments
- Neurological disorders and treatments
- Constraint Satisfaction and Optimization
- Medical Image Segmentation Techniques
- Botulinum Toxin and Related Neurological Disorders
- Semantic Web and Ontologies
- Multi-Agent Systems and Negotiation
- Anomaly Detection Techniques and Applications
- Robotics and Sensor-Based Localization
- Alzheimer's disease research and treatments
University of Ljubljana
2012-2024
University of Zagreb
2013-2022
Institute of Oncology Ljubljana
1994-2018
Ljubljana University Medical Centre
2012-2014
Research Institute of General Pathology and Pathophysiology, the Russian Academy of Medical Sciences
2013
Royal College of Physicians and Surgeons of Canada
2011
University of Ottawa
2011
Parkinson's Clinic of Eastern Toronto & Movement Disorders Centre
2011
Elektro Ljubljana (Slovenia)
1988
Baylor College of Medicine
1981
This paper presents a multimodal biometric identification system based on the features of human hand. We describe new approach to personal using eigenfinger and eigenpalm features, with fusion applied at matching-score level. The process can be divided into following phases: capturing image; preprocessing; extracting normalizing palm strip-like finger subimages; K-L transform; matching fusion; and, finally, decision (k, l)-NN classifier thresholding. was tested database 237 people (1,820...
Phase synchronization between cardiac and respiratory oscillations is investigated during anesthesia in rats. Synchrograms time evolution of indices are used to show that the system passes reversibly through a sequence different phase-synchronized states as level changes, indicating it can undergo phase transitionlike phenomena. It appears state may be characterize depth anesthesia.
We hypothesized that, associated with the state of anaesthesia, characteristic changes exist in both cardio‐respiratory and cerebral oscillator parameters couplings, perhaps varying depth anaesthesia. Electrocardiograms (ECGs), respiration electroencephalograms (EEGs) were recorded from two groups 10 rats during entire course anaesthesia following administration a single bolus ketamine–xylazine (KX group) or pentobarbital (PB group). The phase dynamics approach was then used to extract...
Type 2 diabetes (T2D) and Parkinson’s disease (PD) are chronic disorders that have a significant health impact on global scale. Epidemiological, preclinical, clinical research underpins the assumption insulin resistance inflammation contribute to overlapping aetiologies of T2D PD. This narrative review summarises recent evidence contribution initiation progression PD brain pathology. It also briefly discusses rationale potential alternative pharmacological interventions for treatment.
Publicly captured surveillance videos and images serve as a rich source of biometric identifiers. Of these, the face is one most frequently used for identification people. In order to protect person's identity, whenever it not absolutely required, should be de-identified. One problems that any naturalness-preserving de-identification method address variation in pose. this paper we build several active appearance models on database then use them detect pose well gallery faces...
Face-based identification is used in various application scenarios - from of a person based on still images passport or identity card, to face captured by surveillance system without the cooperation person. In many scenarios, especially video surveillance, privacy can be compromised. One approaches preservation de-identification, where de-identification process concealing removing personal identifiers, replacing them with surrogate identifiers information, multimedia content, order prevent...
Postural instability has a big impact on the quality of life patients with Parkinson's disease (PD) as it often leads to an insecure stance and fall. We investigated if postural stability in these improves by decreasing rigidity dopaminergic agonist. In our study, we tested eight PD no concomitant diseases. Their age was 61 ± 2 years (mean SE) their Hoehn‐Yahr score 3 0.1. The were evaluated according Unified Disease Rating Scale for motor function (mUPDRS) stabilometric measurements...
This paper introduces a new approach in image registration, that is multisensor registration Hough parameter space. Visual and thermal images of building fronts were aimed to be aligned order inspect properties buildings. Some preprocessing visible was necessary comparable their counterparts, namely downsampling color space conversion from RGB grayscale intensity. For each pair, edges detected with Canny edge detector and, as result, binary obtained. These further processed by transform...