1. Approximate local reflection symmetry of projected land cadastre dataIvana Kolingerová, Ondřej Anděl, Eliška Mourycová, Pavel Slavík, Lukáš Hruda, David Podgorelec, Borut Žalik, Ivo Malý, Martin Maňák, 2025, izvirni znanstveni članek Opis: Symmetry is an essential feature of many geometric objects. However, the world also contains many asymmetrical or approximately symmetrical objects. Detecting approximate symmetries is a rather weakly defined problem, as computer-detected approximate symmetry may not correspond to human opinion. The situation is even worse if the symmetry is not global but local. This paper investigates whether approximate local reflection symmetries found by a computer in real data are acceptable for human observers. To answer this question, a new simple approximate local reflection symmetry detection is proposed and run on land cadastre data in the form of planar point sets. The resulting symmetries are subject to user tests to study human acceptance of approximate local symmetry. The results show a relatively good correlation between symmetry detected by computers and perceived by humans. This finding provides a solid foundation for integrating both approaches in specific applications. To achieve this, further research is needed on how to utilize specific aspects of human symmetry perception in computer solutions, so that computer symmetry detection can better approximate human perception.
Ključne besede: symmetry, geodata, computer graphics, human perception
Objavljeno v DKUM: 09.12.2025; Ogledov: 0; Prenosov: 1
 Celotno besedilo (2,36 MB) |
2. Primerjava odpornosti slikovnih datotečnih formatov na okvare podatkovŽan Kelbič, 2025, diplomsko delo Opis: V diplomskem delu smo primerjali odpornost slikovnih formatov JPEG, JPEG2000, PNG, WebP, TIFF in HEIF ob nadzorovanih okvarah bitnega toka z namenom ugotavljanja njihovih prednosti, slabosti in zmožnosti dekodiranja. Okvare smo vnašali z metodami preklopa bitov, prepisa zlogov, zamenjave segmentov, metode "fuzzing" in krajšanjem datotek. Objektivne podobnosti med referenčnimi in okvarjenimi slikami smo merili z metrikama PSNR in SSIM. Na osnovi reprezentativnih vzorcev pri naključnih eksperimentih smo podali ugotovitve o odpornosti posameznih formatov na okvare.
Ključne besede: slikovni datotečni formati, okvare slik, odpornost na okvare, JPEG, JPEG2000, PNG, WebP, TIFF, HEIF, PSNR, SSIM
Objavljeno v DKUM: 17.10.2025; Ogledov: 0; Prenosov: 6
Celotno besedilo (7,01 MB) |
3. Uporaba evolucijskega računanja za zmanjšanje zaznave napak pri stresanju rastrskih slik : diplomsko deloBlaž Vidovič, 2025, diplomsko delo Opis: Diplomsko delo obravnava stresanje rastrskih slik in njegovo optimizacijo. Z namenom zmanjšanja zaznave napake smo matriko algoritma za stresanje Jarvis, Judice in Ninke prilagodili s pomočjo diferencialne evolucije. Skozi optimizacijo smo spreminjali uteži v matriki tako, da smo se poskušali s stresano sliko čim bolj približati originalni sliki. Za merjenje podobnosti med dvema slikama smo uporabili metriki PSNR in SSIM. Z večkratnim zagonom optimizacije smo analizirali vpliv različnih parametrov diferencialne evolucije na kakovost končnega rezultata. Ugotovili smo, da izboljšan SSIM ne pomeni nujno boljše ujemanje stresane slike z originalno sliko.
Ključne besede: rastrska slika, stresanje, Jarvis Judice in Ninke, optimizacija, evolucijski algoritmi, diferencialna evolucija
Objavljeno v DKUM: 23.09.2025; Ogledov: 0; Prenosov: 13
Celotno besedilo (3,60 MB) |
4. Prunability of multi-layer perceptrons trained with the forward-forward algorithmMitko Nikov, Damjan Strnad, David Podgorelec, 2025, izvirni znanstveni članek Opis: We explore the sparsity and prunability of multi-layer perceptrons (MLPs) trained using the Forward-Forward (FF) algorithm, an alternative to backpropagation (BP) that replaces the backward pass with local, contrastive updates at each layer. We analyze the sparsity of the weight matrices during training using multiple metrics, and test the prunability of FF networks on the MNIST, FashionMNIST and CIFAR-10 datasets. We also propose FFLib—a novel, modular PyTorch-based library for developing, training and analyzing FF models along with a suite of FF-based architectures, including FFNN, FFNN+C and FFRNN. In addition to structural sparsity, we describe and apply a new method for visualizing the functional sparsity of neural activations across different architectures using the HSV color space. Moreover, we conduct a sensitivity analysis to assess the impact of hyperparameters on model performance and sparsity. Finally, we perform pruning experiments, showing that simple FF-based MLPs exhibit significantly greater robustness to one-shot neuron pruning than traditional BP-trained networks, and a possible 8-fold increase in compression ratios while maintaining comparable accuracy on the MNIST dataset.
Ključne besede: Forward-Forward, sparsity, pruning, model compression, machine learning, neural network
Objavljeno v DKUM: 20.08.2025; Ogledov: 0; Prenosov: 4
Celotno besedilo (7,01 MB) |
5. A hierarchical universal algorithm for geometric objects’ reflection symmetry detectionBorut Žalik, Damjan Strnad, Štefan Kohek, Ivana Kolingerová, Andrej Nerat, Niko Lukač, David Podgorelec, 2022, izvirni znanstveni članek Opis: A new algorithm is presented for detecting the global reflection symmetry of geometric
objects. The algorithm works for 2D and 3D objects which may be open or closed and may or may
not contain holes. The algorithm accepts a point cloud obtained by sampling the object’s surface at
the input. The points are inserted into a uniform grid and so-called boundary cells are identified.
The centroid of the boundary cells is determined, and a testing symmetry axis/plane is set through
it. In this way, the boundary cells are split into two parts and they are faced with the symmetry
estimation function. If the function estimates the symmetric case, the boundary cells are further split
until a given threshold is reached or a non-symmetric result is obtained. The new testing axis/plane
is then derived and tested by rotation around the centroid. This paper introduces three techniques to
accelerate the computation. Competitive results were obtained when the algorithm was compared
against the state of the art.
Ključne besede: computer science, computational geometry, uniform subdivision, centroids
Objavljeno v DKUM: 01.04.2025; Ogledov: 0; Prenosov: 8
Celotno besedilo (2,99 MB)
Gradivo ima več datotek! Več... |
6. Survey of inter-prediction methods for time-varying mesh compressionJan Dvořák, Filip Hácha, Gerasimos Arvanitis, David Podgorelec, Konstantinos Moustakas, Libor Váša, 2025, izvirni znanstveni članek Opis: Time-varying meshes (TVMs), that is mesh sequences with varying connectivity, are a greatly versatile representation of shapesevolving in time, as they allow a surface topology to change or details to appear or disappear at any time during the sequence.This, however, comes at the cost of large storage size. Since 2003, there have been attempts to compress such data efficiently. Whilethe problem may seem trivial at first sight, considering the strong temporal coherence of shapes represented by the individualframes, it turns out that the varying connectivity and the absence of implicit correspondence information that stems from itmakes it rather difficult to exploit the redundancies present in the data. Therefore, efficient and general TVM compression is stillconsidered an open problem. We describe and categorize existing approaches while pointing out the current challenges in thefield and hint at some related techniques that might be helpful in addressing them. We also provide an overview of the reportedperformance of the discussed methods and a list of datasets that are publicly available for experiments. Finally, we also discusspotential future trends in the field.
Ključne besede: compression algorithms, data compression, modelling, polygonal mesh reduction
Objavljeno v DKUM: 07.02.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (3,11 MB) |
7. |
8. State-of-the-art trends in data compression : COMPROMISE case studyDavid Podgorelec, Damjan Strnad, Ivana Kolingerová, Borut Žalik, 2024, izvirni znanstveni članek Opis: After a boom that coincided with the advent of the internet, digital cameras, digital video and audio storage and playback devices, the research on data compression has rested on its laurels for a quarter of a century. Domain-dependent lossy algorithms of the time, such as JPEG, AVC, MP3 and others, achieved remarkable compression ratios and encoding and decoding speeds with acceptable data quality, which has kept them in common use to this day. However, recent computing paradigms such as cloud computing, edge computing, the Internet of Things (IoT), and digital preservation have gradually posed new challenges, and, as a consequence, development trends in data compression are focusing on concepts that were not previously in the spotlight. In this article, we try to critically evaluate the most prominent of these trends and to explore their parallels, complementarities, and differences. Digital data restoration mimics the human ability to omit memorising information that is satisfactorily retrievable from the context. Feature-based data compression introduces a two-level data representation with higher-level semantic features and with residuals that correct the feature-restored (predicted) data. The integration of the advantages of individual domain-specific data compression methods into a general approach is also challenging. To the best of our knowledge, a method that addresses all these trends does not exist yet. Our methodology, COMPROMISE, has been developed exactly to make as many solutions to these challenges as possible inter-operable. It incorporates features and digital restoration. Furthermore, it is largely domain-independent (general), asymmetric, and universal. The latter refers to the ability to compress data in a common framework in a lossy, lossless, and near-lossless mode. COMPROMISE may also be considered an umbrella that links many existing domain-dependent and independent methods, supports hybrid lossless–lossy techniques, and encourages the development of new data compression algorithms
Ključne besede: data compression, data resoration, universal algorithm, feature, residual
Objavljeno v DKUM: 04.02.2025; Ogledov: 0; Prenosov: 14
Celotno besedilo (1,13 MB) |
9. A case study on entropy-aware block-based linear transforms for lossless image compressionBorut Žalik, David Podgorelec, Ivana Kolingerová, Damjan Strnad, Štefan Kohek, 2024, izvirni znanstveni članek Opis: Data compression algorithms tend to reduce information entropy, which is crucial, especially in the case of images, as they are data intensive. In this regard, lossless image data compression is especially challenging. Many popular lossless compression methods incorporate predictions and various types of pixel transformations, in order to reduce the information entropy of an image. In this paper, a block optimisation programming framework is introduced to support various experiments on raster images, divided into blocks of pixels. Eleven methods were implemented within , including prediction methods, string transformation methods, and inverse distance weighting, as a representative of interpolation methods. Thirty-two different greyscale raster images with varying resolutions and contents were used in the experiments. It was shown that reduces information entropy better than the popular JPEG LS and CALIC predictors. The additional information associated with each block in is then evaluated. It was confirmed that, despite this additional cost, the estimated size in bytes is smaller in comparison to the sizes achieved by the JPEG LS and CALIC predictors.
Ključne besede: computer science, information entropy, prediction, inverse distance transform, string transformations
Objavljeno v DKUM: 07.01.2025; Ogledov: 0; Prenosov: 10
Celotno besedilo (5,13 MB) |
10. |
