Peter Leskovsky

Dr. Peter Leskovsky

orcid
avatar
Co-authors
avatar
Following
avatar
Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2022
Verified
Conference Paper
Open access
DMDavid Montero
David Montero
Marcos NietoMarcos Nieto
Marcos Nieto
PLPeter Leskovsky
Peter Leskovsky
NBNaiara Aginako Bengoa
Naiara Aginako Bengoa
In this article, we tackle the recognition of faces wearing surgical masks. Surgical masks have become a necessary piece of daily apparel because of the COVID-19-related worldwide health problem. Modern face recognition models are in trouble because they were not made to function with masked faces. Furthermore, in order to stop the infection from spreading, apps capable of detecting if the individuals are wearing masks are also required. To address these issues, we present an end-to-end approach for training face recognition models based on the ArcFace architecture, including various changes to the backbone and loss computation. We also use data augmentation to generate a masked version of the original dataset and mix them on the fly while training. Without incurring any additional computational costs, we modify the chosen network to output also the likelihood of wearing a mask. Thus, the face recognition loss and the mask-usage loss are merged to create a new function known as Multi-Task ArcFace (MTArcFace). The conducted experiments demonstrate that our method outperforms the baseline model results when faces with masks are considered, while achieving similar metrics on the original dataset. In addition, it obtains a 99.78% of mean accuracy in mask-usage classification.
4 October 2012 in Diagnostic Pathology
Verified
Journal Article
Open access
PDF file
HSHarshita Sharma
Harshita Sharma
AAAlexander Alekseychuk
Alexander Alekseychuk
PLPeter Leskovsky
Peter Leskovsky
OHOlaf Hellwich
Olaf Hellwich
RARs Anand
Rs Anand
PHPeter Hufnagl
Peter Hufnagl
Computer-based analysis of digitalized histological images has been gaining increasing attention, due to their extensive use in research and routine practice. The article aims to contribute towards the description and retrieval of histological images by employing a structural method using graphs. Due to their expressive ability, graphs are considered as a powerful and versatile representation formalism and have obtained a growing consideration especially by the image processing and computer vision community.
8 December 2017 in Frontiers in Neuroinformatics
Verified
Journal Article
Open access
AMAndoni Mujika
Andoni Mujika
PLPeter Leskovsky
Peter Leskovsky
RÁRoberto Álvarez
Roberto Álvarez
MOMiguel A. Otaduy
Miguel A. Otaduy
Gorka EpeldeGorka Epelde
Gorka Epelde
This paper focusses on the simulation of the neural network of the Caenorhabditis elegans living organism, and more specifically in the modeling of the stimuli applied within behavioral experiments and the stimuli that is generated in the interaction of the C. elegans with the environment. To the best of our knowledge, all efforts regarding stimuli modeling for the C. elegansare focused on a single type of stimulus, which is usually tested with a limited subnetwork of the C. elegansneural system. In this paper, we follow a different approach where we model a wide-range of different stimuli, with more flexible neural network configurations and simulations in mind. Moreover, we focus on the stimuli sensation by different types of sensory organs or various sensory principles of the neurons. As part of this work, most common stimuli involved in behavioral assays have been modeled. It includes models for mechanical, thermal, chemical, electrical and light stimuli, and for proprioception-related self-sensed information exchange with the neural network. The developed models have been implemented and tested with the hardware-based Si elegans simulation platform.
1 May 2018 in Neurocomputing
Verified
Journal Article
Open access
ACAlicia Costalago-Meruelo
Alicia Costalago-Meruelo
Pedro MachadoPedro Machado
Pedro Machado
KAKofi Appiah
Kofi Appiah
AMAndoni Mujika
Andoni Mujika
PLPeter Leskovsky
Peter Leskovsky
TMThomas Martin McGinnity
Thomas Martin McGinnity
7 March 2023 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
DMDavid Montero
David Montero
Nerea AranjueloNerea Aranjuelo
Nerea Aranjuelo
PLPeter Leskovsky
Peter Leskovsky
ELEstíbaliz Loyo
Estíbaliz Loyo
Marcos NietoMarcos Nieto
Marcos Nieto
NBNaiara Aginako Bengoa
Naiara Aginako Bengoa
The current sanitary emergency situation caused by COVID-19 has increased the interest in controlling the flow of people in indoor infrastructures, to ensure compliance with the established security measures. Top view camera-based solutions have proven to be an effective and non-invasive approach to accomplish this task. Nevertheless, current solutions suffer from scalability problems: they cover limited range areas to avoid dealing with occlusions and only work with single camera scenarios. To overcome these problems, we present an efficient and scalable people flow monitoring system that relies on three main pillars: an optimized top view human detection neural network based on YOLO-V4, capable of working with data from cameras at different heights; a multi-camera 3D detection projection and fusion procedure, which uses the camera calibration parameters for an accurate real-world positioning; and a tracking algorithm which jointly processes the 3D detections coming from all the cameras, allowing the traceability of individuals across the entire infrastructure. The conducted experiments show that the proposed system generates robust performance indicators and that it is suitable for real-time applications to control sanitary measures in large infrastructures. Furthermore, the proposed projection approach achieves an average positioning error below 0.2 meters, with an improvement of more than 4 times compared to other methods.
25 May 2006
Verified
Conference Paper
Closed access
PLPeter Leskovsky
Peter Leskovsky
MHM. Harders
M. Harders
GSG. Szeekely
G. Szeekely
A central element of surgical simulators is the generation of appropriate haptic feedback. Several factors influence this rendering process, which could potentially degrade the feedback quality. In this context, our current research aims at assessing, how well haptic sensations encountered during interaction with real objects, can actually be approximated in a virtual environment. Since finding appropriate soft tissue deformation models for real time interaction is a complex task in itself, we limited the investigations in this pilot study to simple linear-elastic silicone objects. A model of a virtual deformable object was adapted and parameters selected to approximate a real silicone sample within a specific hardware setup. A comparative study was performed, in which 13 subjects had to discriminate between the categories of real and virtual objects. We found that subjects could discern between the categories with a mean accuracy of 63% with no significant bias towards assuming the presence of either real or virtual objects. While being above chance level, the results indicate that we were able to approximate haptic feedback of a real object with high fidelity in our specific hardware setup.