Filters
total: 31383
-
Catalog
displaying 1000 best results Help
Search results for: PROCESSING AND IMAGE ANALYSIS
-
Autonomous pick-and-place system based on multiple 3Dsensors and deep learning
PublicationGrasping objects and manipulating them is the main way the robot interacts with its environment. However, for robots to operate in a dynamic environment, a system for determining the gripping position for objects in the scene is also required. For this purpose, neural networks segmenting the point cloud are usually applied. However, training such networks is very complex and their results are unsatisfactory. Therefore, we propose...
-
Autonomous Perception and Grasp Generation Based on Multiple 3D Sensors and Deep Learning
PublicationGrasping objects and manipulating them is the main way the robot interacts with its environment. However, for robots to operate in a dynamic environment, a system for determining the gripping position for objects in the scene is also required. For this purpose, neural networks segmenting the point cloud are usually applied. However, training such networks is very complex and their results are unsatisfactory. Therefore, we propose...
-
Zdolności dynamiczne do budowania chmury wartości w modelach biznesów
PublicationObserwacja współczesnych metod tworzenia wartości daje podstawy do wyłonienia nowej logiki ich generowania. Analiza modeli wytwarzania wartości przez przedsiębiorstwa np. sieciowe wykazała, że formułują one chmury wartości. Struktury tych chmur są różnorodne, niejednolite, kłębiaste. Przeprowadzone prace pozwoliły na sformułowanie obrazów wartości generowanych przez twarde komponenty modeli biznesów. Osiągnięcie tych wyników pozwoliło...
-
Metoda TrustCritic oceny wiarygodności sklepów internetowych
PublicationW artykule przedstawiono metodę oceny wiarygodności sklepów internetowych TrustCritic. Powszechnie występujące nadużycia w handlu elektronicznym sprawiają, że zaufanie do przedsiębiorcy staje się kluczowym czynnikiem decyzji konsumentów. Przedsiębiorca narażony jest na niezgodność z prawem, utratę wizerunku i klientów. Artykuł omawia problematykę nadużyć w sferze e-biznesu oraz proponuje wielokryterialny model oceny sklepu internetowego,...
-
Optimal selection of input features and an acompanying neural network structure for the classification purposes - skin lesions case study
PublicationMalignant melanomas are the most deadly type of skin cancers however detected early enough give a high chances for successful treatment. The last years saw the dynamic growth of interest of automatic computer-aided skin cancer diagnosis. Every month brings new research results on new approaches to this problem, new methods of preprocessing, new classifiers, new ideas to follow etc. In particular, the rapid development of dermatoscopy,...
-
Network oscillations modulate interictal epileptiform spike rate during human memory
PublicationEleven patients being evaluated with intracranial electroencephalography for medically resistant temporal lobe epilepsy participated in a visual recognition memory task. Interictal epileptiform spikes were manually marked and their rate of occurrence compared between baseline and three 2 s periods spanning a 6 s viewing period. During successful, but not unsuccessful, encoding of the images there was a significant reduction in...
-
Analiza bibliometryczna w badaniach dotyczących prognozowania upadłości przedsiębiorstw w Polsce
PublicationCelem opracowania jest ukazanie obrazu piśmiennictwa poświęconego zagadnieniom prognozowania upadłości przedsiębiorstw w Polsce. Jako metodę badawczą zastosowano analizę bibliometryczną. Do analizy wykorzystano bazę Google Scholar oraz narzędzie Publish or Perish 7. Okresem badań objęto lata 1995– 2019. Jako frazy do wyszukiwania publikacji zastosowano: „prognozowanie upadłości”, „prognozowanie zagrożenia finansowego”, „systemy...
-
Strategie treningu neuronowego estymatora częstotliwości tonu krtaniowego z użyciem generatora syntetycznych samogłosek
PublicationW wielu zastosowaniach telekomunikacyjnych pojawia się problem przetwarzania lub analizy sygnału mowy, w ramach którego, często w obszarze podstawowych algorytmów, stosuje się estymator częstotliwości tonu krtaniowego. Estymator rozpatrywany w tej pracy bazuje na neuronowym klasyfikatorze podejmującym decyzje na podstawie częstotliwości oraz mocy chwilowej wyznaczanych w podpasmach analizowanego sygnału mowy. W pracy rozważamy...
-
Interpretable deep learning approach for classification of breast cancer - a comparative analysis of multiple instance learning models
PublicationBreast cancer is the most frequent female cancer. Its early diagnosis increases the chances of a complete cure for the patient. Suitably designed deep learning algorithms can be an excellent tool for quick screening analysis and support radiologists and oncologists in diagnosing breast cancer.The design of a deep learning-based system for automated breast cancer diagnosis is not easy due to the lack of annotated data, especially...
-
Orbital blowout trauma occurring at the workplace – clinical, biomechanical and legal aspects
PublicationIntroduction and objective: Craniofacial injury at the workplace may lead to orbital blowout fractures. The aim of the study is the development of own numerical model of the eye orbit, assessment of the damage zones, and comparing them with clinical examinations. In addition, the current legal status of patients after injuries is presented Material and methods: In laboratory tests performed on bones collected from the upper and...
-
Selection of an artificial pre-training neural network for the classification of inland vessels based on their images
PublicationArtificial neural networks (ANN) are the most commonly used algorithms for image classification problems. An image classifier takes an image or video as input and classifies it into one of the possible categories that it was trained to identify. They are applied in various areas such as security, defense, healthcare, biology, forensics, communication, etc. There is no need to create one’s own ANN because there are several pre-trained...
-
ANN for human pose estimation in low resolution depth images
PublicationThe paper presents an approach to localize human body joints in 3D coordinates based on a single low resolution depth image. First a framework to generate a database of 80k realistic depth images from a 3D body model is described. Then data preprocessing and normalization procedure, and DNN and MLP artificial neural networks architectures and training are presented. The robustness against camera distance and image noise is analysed....
-
AN ALGORITHM FOR PORTAL HYPERTENSIVE GASTROPATHY RECOGNITION ON THE ENDOSCOPIC RECORDINGS
PublicationSymptoms recognition of portal hypertensive gastropathy (PHG) can be done by analysing endoscopic recordings, but manual analysis done by physician may take a long time. This increases probability of missing some symptoms and automated methods may be applied to prevent that. In this paper a novel hybrid algorithm for recognition of early stage of portal hypertensive gastropathy is proposed. First image preprocessing is described....
-
Towards Synthetic and Balanced Digital Government Benchmarking
PublicationReliable benchmarking is essential for effective management of the government digitalization efforts. Existing benchmarking instruments generally fail to support this target. One problem is the diversity of instruments, resulting in a split image of digital progress and adding ambiguity to policy decisions. Another problem is disconnect in assessing progress between digital and traditional “analog” governance, lending support to...
-
Reversible Data Hiding in Encrypted DICOM Images Using Cyclic Binary Golay (23, 12) Code
PublicationIn this paper, a novel reversible data hiding method for encrypted images (RDHEI) is proposed. An efficient coding scheme based on cyclic binary Golay (23, 12) code is designed to embed additional data into the least significant bits (LSBs) of the encrypted image. The most significant bits (MSBs) are used to ensure the reversibility of the embedding process. The proposed scheme is lossless, and based on the receiver’s privileges,...
-
A model of the response of the MGS-6 gravity sensor to tilting
PublicationThe reliable interpretation of the measurements made by the Micro-g marine gravimetric system (MGS-6) depends on how the temporary changes of the scale coefficients such as gravimeter scale factor, vertical cross-coupling (VCC) effect, tiltmeter cross and tiltmeter long are compensated for during the signal analysis. The listed coefficients cannot be determined from readings during the measurements or by analysing the final data....
-
Process zone in the Single Cantilever Beam under transverse loading. - Part II: Experimental
PublicationThis paper describes an experimental arrangement to evaluate stress/strain fields in the process zone of asymmetric adhesively bonded joints. A transparent polycarbonate flexible beam was bonded to an aluminium alloy rigid block with an epoxy adhesive in a Single Cantilever Beam (SCB) configuration. The flexible adherend was loaded in the direction parallel to the initial crack front at constant rate. To monitor strains induced...
-
Flow field around growing and rising vapour bubble by PIV measurement.
PublicationPrzedstawiono wyniki badania pól prędkości wokół wzrastających i unoszących się pęcherzyków parowych generowanych z pojedynczego centrum nukleacji. W badaniach zastosowano komercyjny układ Particle Image Velocimetry.
-
Corporate Governance and Ownership Structure in the Top 30 Listed Non Financial Companies in Poland
PublicationThis paper offers a first analysis of the relationships between corporate governance models and rules and ownership structure of the top 30 Polish firms listed at the WSE (not considering foreign firms and/or the Polish branches of foreign firms listed at the same stock exchange, nor the financial companies and the banks). The general picture depicted by this analysis is putting into evidence the increasing importance of institutional...
-
Performance Analysis of Developed Multimodal Biometric Identity Verification System
PublicationThe bank client identity verification system developed in the course of the IDENT project is presented. The total number of five biometric modalities including: dynamic handwritten signature proofing, voice recognition, face image verification, face contour extraction and hand blood vessels distribution comparison have been developed and studied. The experimental data were acquired employing multiple biometric sensors installed...
-
Evaluation of open drone map toolkit for geodetic grade aerial drone mapping – case study
PublicationAn open source tool’s popularity has increased considerably, as well as micro aerial vehicles (MAV) technologies based on open source hardware. An open source software and hardware delivers a wide variety of applications and technology. The world’s most successful open source projects have their roots in the academy, and now its participation includes a wide variety of academic programs and research. Based on open source technology,...
-
User experience evaluation study on the quality of 1K, 2K, and 4K H.265/HEVC video content
PublicationNowadays, most content creators focus on distributing rich media at the highest possible resolution. Currently, the majority of sold consoles, media players, computer hardware, as well as displays and TVs are advertised as 4K-compatible. The same trend is observed in the case of popular online streaming services and terrestrial TV broadcasts. Generally speaking, it is assumed that higher bitrates provide higher subjective judgements....
-
Zastosowanie techniki PIV do wyznaczania przemieszczeń podłoża gruntowego
PublicationPrzedstawiono nową metodę wyznaczania przemieszczeń podłoża gruntowego za pomocą techniki PIV (Particle Image Velocimetry). Zamieszczono przykładowe wyniki własnych badań modelowych stateczności fundamentów bezpośrednich uzyskane tą metodą.
-
Mechanical and fracture properties of concrete reinforced with recycled and industrial steel fibers using Digital Image Correlation technique and X-ray micro computed tomography
PublicationPaper presents investigation of fracture phenomenon in plain concrete and in concrete reinforced with both recycled steel fibers (RSF) and industrial steel fibers (ISF). The wedge splitting test (WST), which enables stable crack propagation for quasi-brittle materials, was carried out on 75 75 75 mm cube samples. Initially, fracture process zone development was investigated only on the surface of samples using Digital Image Correlation...
-
Andrzej Chybicki dr inż.
PeopleA graduate of the Faculty of Electronics, Telecommunications and Informatics at the Gdańsk University of Technology, PhD in technical sciences in the field of IT specializing in distributed data processing in IT . Aimed at exploiting the achievements and knowledge in the field of industrial research. He cooperated with a number of companies including OpeGieka Elbląg, Reson Inc., Powel Sp. z o. o., Wasat, Better Solutions, the European...
-
Reconstruction of 3D structure of positive corona streamer by local methods
PublicationThe computer algorithms were used for reconstruction of streamer 3D structure. We propose the 3D tree structure model of corona discharge streamer composed with nodes and edges between chosen couples of nodes, which enables easy computation of some important parameters ofstreamers. The 3D model can be derived directly from two projection images by global methods like evolutionary searching or particle simulations. In this paper...
-
Tracking Fluorescent Dye Dispersion from an Unmanned Aerial Vehicle
PublicationCommercial unmanned aerial vehicles continue to gain popularity and their use for collecting image data and recording new phenomena is becoming more frequent. This study presents an effective method for measuring the concentration of fluorescent dyes (fluorescein and Rhodamine WT) for the purpose of providing a mathematical dispersion model. Image data obtained using a typical visible-light camera was used to measure the concentration...
-
Rola GIS w badaniach środowiska morskiego
PublicationŚrodowisko morskie nadal pozostaje „białą plamą” z punktu widzenia systemów GIS. Trudno jest znaleźć analogie pomiędzy cyfrowym modelem terenu a danymi batymetrycznymi, ponieważ odzwierciedlają one tylko jedno z możliwych obliczy środowiska morskiego, drugim bardzo ważnym, jest falowanie. Jednakże dopiero informacja wspólna o batymetrii i falowaniu jest naprawdę wartościowa dla ludzi korzystających z morza zawodowo. Mając do dyspozycji...
-
ARCHITECTURE IN BRANDING AND OVERBRANDING PROCESS. HOW GLOBALIZATION INFLUENCED ARCHITECTURE QUALITY.
PublicationGlobalization is unification. In the field of architecture and in the social structure alike, the globalization leads to a blending of economies and cultures that produces uniformly branded public space as a response to universal assumptions of integration and correlation. While branding consists in creating a recognizable and outstanding image a strong contradiction exists between both of these approaches. As a result, regional...
-
Buried Object Characterization by Data-Driven Surrogates and Regression-Enabled Hyperbolic Signature Extraction
PublicationThis work addresses artificial-intelligence-based buried object characterization using FDTD-based electromagnetic simulation toolbox of a Ground Penetrating Radar (GPR) to generate B-scan data. In data collection, FDTD-based simulation tool, gprMax is used. The task is to estimate geophysical parameters of a cylindrical shape object of various radii, buried at different positions in the dry soil medium simultaneously and independently...
-
Barcelona - from the province to Metropolis.The cogent strategy of branding the city
PublicationThe phenomenon of rebranding Barcelona's image, called the Barcelona effect or 'Barcelona Model', is exampled as one of the most spectacular transformations of the city perception in the last decade. Why has Barcelona been successful? Is it the effect of the recently intensified revitalization practice, or has the city of Barcelona built its brand market value for years? The aim of the research is to name these transition...
-
Niemetryczne zdjęcia cyfowe w fotogrametrii bliskiego zasięgu w systemie Topcon PI - 3000
PublicationReferat jest opisem możliwośći opracowania obiektu architektonicznego w systemie Topcon Image Surveying Station PI - 3000. Prezentuje możliwości współczesnej fotogrametrii cyfrowej opartej na niemetrycznych obrazach pozyskanych z amatorskich aparatów cyfrowych.
-
Physicochemical Problems of Mineral Processing
Journals -
Marek Czachor prof. dr hab.
People -
From Linear Classifier to Convolutional Neural Network for Hand Pose Recognition
PublicationRecently gathered image datasets and the new capabilities of high-performance computing systems have allowed developing new artificial neural network models and training algorithms. Using the new machine learning models, computer vision tasks can be accomplished based on the raw values of image pixels instead of specific features. The principle of operation of deep neural networks resembles more and more what we believe to be happening...
-
The green waterfront of a city. Where are the limits of good planning? Gdansk case
PublicationThe aim of the article is to present the role of green public areas of waterfronts in shaping the image of cities, and the threats to such landscape which may be caused by wrong planning decisions. The case study of Gdansk sea-shore area in Poland is presented as an example to illustrate the values and potential of the waterfront landscape which can be easily destroyed by inadequate spatial development. Some theoretical studies...
-
Pilot Testing of Developed Multimodal Biometric Identity Verification System
PublicationThe bank client identity verification system developed in the course of the IDENT project is presented. The total number of five biometric modalities including: dynamic signature proofing, voice recognition, face image verification, face contour extraction and hand blood vessels distribution comparison have been developed and studied. The experimental data were acquired employing multiple biometric sensors installed at engineered...
-
Numerical investigations of discrete crack propagation in Montevideo splitting test using cohesive elements and real concrete micro-structure
PublicationThe paper is aimed at accurately predicting the discrete fracture process in concrete specimens under complex stress states in two dimensional (2D) simulations. Plain concrete specimens subjected to Montevideo splitting test (MVD) were used for consideration due to non-negligible shear stresses impact in this type of test. In order to reflect the heterogeneous nature of the concrete, the meso-structure of the samples was included...
-
Objects classification based on their physical sizes for detection of events in camera images
PublicationIn the paper, a method of estimation of the physical sizes of the objects tracked in the video surveillance system, and a simple module for object classification based on the estimated physical sizes, are presented. The results of object classification are then used for automatic detection of various types of events in the camera image.
-
Sources and composition of chemical pollution in Maritime Antarctica (King George Island), part 1: Sediment and water analysis for PAH sources evaluation in the vicinity of Arctowski station
PublicationThe paper presents a study regarding the identification of polycyclic aromatic hydrocarbons (PAHs) in fresh waters and surface sediments on the western shore of Admiralty Bay over four sampling seasons from 2017 to 2018. The results were compared to literature data from 2016 to provide a more comprehensive image of the environmental fate of PAHs over the years. The highest value of Σ PAHs was 82.9 ng/L and 445 ng/g dw in water...
-
Pose-Configurable Generic Tracking of Elongated Objects
PublicationElongated objects have various shapes and can shift, rotate, change scale, and be rigid or deform by flexing, articulating, and vibrating, with examples as varied as a glass bottle, a robotic arm, a surgical suture, a finger pair, a tram, and a guitar string. This generally makes tracking of poses of elongated objects very challenging. We describe a unified, configurable framework for tracking the pose of elongated objects, which...
-
Shear fracture of longitudinally reinforced concrete beams under bending using Digital Image Correlation and FE simulations with concrete micro-structure based on X-ray micro-computed tomography images
PublicationThe paper presents experimental and numerical investigations of the shear fracture in rectangular concrete beams longitudinally reinforced with steel or basalt bar under quasi-static three point bending. Shear fracture process zone formation and development on the surface of beams was investigated by Digital Image Correlation (DIC) whereas thorough analyses of 3D material micro-structure, air voids, width and curvature of shear...
-
Uniqueness or uniformity - studies of media architecture
PublicationA development of media architecture is presented in light of to such phenomena as aesthetization, consumerism and digitization. This article deals with media architecture in commercial spaces. Media solutions impact on the architectural skin, making it into visible and dynamic points of the image of a post-modern city. This article presents the specificity of media solutions, depending on the function of commercial activity buildings...
-
Błażej Prusak dr hab.
PeopleBłażej Prusak is Head of the Department of Finance at the Faculty of Management and Economics, Gdansk University of Technology and Editor-in-Chief of the journal Research on Enterprise in Modern Economy - theory and practice (REME), as well as a member of editorial boards of such journals as Intellectual Economics; Space. Economics. Society; Academy of Management. He is the author or co-author of several scientific monographs including:...
-
Combined spline wavelet decomposition for 3d seafloor imaging from multibeam sonar echoes
PublicationThe paper proposes combined spline-wavelet approach to the raw echoes seaflor imaging from Multibeam Sonar System (MBSS) records. Wavelet representation is closely related to image representation, due to its unique approximations properties. Splines have the best approximation properties among all known wavelets of a given order, so they are best suited for approximating of smooth seafloor surface. Additionaly, wavelet bases have...
-
Human-Computer Interface Based on Visual Lip Movement and Gesture Recognition
PublicationThe multimodal human-computer interface (HCI) called LipMouse is presented, allowing a user to work on a computer using movements and gestures made with his/her mouth only. Algorithms for lip movement tracking and lip gesture recognition are presented in details. User face images are captured with a standard webcam. Face detection is based on a cascade of boosted classifiers using Haar-like features. A mouth region is located in...
-
Contour Analysis of Bleeding Regions in Endoscopic Images
PublicationThis paper investigates the problem of detecting bleeding regions in images acquired from endoscopic examinations of gastrointestinal tract. The purpose is to identify the characteristic features of bleeding areas' contours in order to develop an accurate method for discriminating between true bleeding regions and missed detections, which could lead to a significant reduction of the false alarm rate of existing blood-detection...
-
Input files for the Floodsar software
Open Research DataInput files for the Floodsar softwareAuthor: Tomasz Berezowski, Gdansk University of Technology, tomberez@eti.pg.edu.pl
-
Computer-Aided Detection of Hypertensive Retinopathy Using Depth-Wise Separable CNN
PublicationHypertensive retinopathy (HR) is a retinal disorder, linked to high blood pressure. The incidence of HR-eye illness is directly related to the severity and duration of hypertension. It is critical to identify and analyze HR at an early stage to avoid blindness. There are presently only a few computer-aided systems (CADx) designed to recognize HR. Instead, those systems concentrated on collecting features from many retinopathy-related...
-
Combining X-ray tomogrpahy imaging and DEM simulations to investigate granular material flow during silo discharging
PublicationEven after few decades of research, the study of particle motion taking place during silo discharging hasn’t been fully addressed, both experimentally and numerically, because of nontrivial behaviors that occur during associated flow patterns. For instance, discrete element method (DEM) has shown good qualitative prediction potential of velocity profile, but, on the other hand, frequently failed to match quantitatively experimental...