Ograniczanie wyników
Czasopisma help
Autorzy help
Lata help
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 732

Liczba wyników na stronie
first rewind previous Strona / 37 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  image processing
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 37 next fast forward last
EN
The article explores how qualitative image analysis impacts the process of image interpretation, particularly in composite microstructure analysis. It highlights the importance of high-quality images for accurate computer-based object detection, emphasizing the limitations of rigid pixel-based rules compared to human visual perception. The study underscores the need for optimal imaging conditions to avoid image defects that hinder precise computational analyses in scientific and industrial applications
EN
The current research is focused on the identification of cargo containers in a stack from their images in the infrared and visible spectra, in order to locate the container-origin of ignition within the cargo temperature control and fire safety system. The relevance of the topic is reinforced by the functional requirements for shipboard safety, which are embodied in Chapter II-2 of the Safety of Life at Sea (SOLAS) Convention, and demanded by the necessity of enhancing safety measures during cargo transportation by the world container fleet. The thermal imager’s field of view (FOV) and the coordinate dependencies between the object and its image have been studied and modelled, and an algorithm for fire detection has been defined within the scope of the current research in connection with the containers within the camera’s FOV. A corresponding verification has been carried out by means of simulation modelling using the Unity and C# programming language capabilities.
EN
We propose a high-quality infrared and visible image fusion method based on a deep wavelet-dense network (WT-DenseNet). The WT-DenseNet includes three network layers, the hybrid feature extraction layer, fusion layer, and image reconstruction layer. The hybrid feature extraction layer is composed of a wavelet and dense network. The wavelet network decomposes the feature map of the visible and infrared images into low-frequency and high-frequency components, respectively. The dense network extracts the salient features. A fusion layer is designed to integrate low-frequency and salient features. Finally, the fusion images are outputted by an image reconstruction layer. The experimental results demonstrate that the proposed method can realize high-quality infrared and visible image fusions, and the performance of the proposed method is better than that of the six recently published fusion methods in terms of contrast and detail performance.
EN
The quality of the powder layers in the 3D printing process is extremely important and directly corresponds to the quality of the structures made with this technology. Therefore, it is essential to control it. It can be made in-line with a vision system combined with image processing algorithms, which can significantly improve control of the process and help with the adjustment of powder spreading systems, especially in case of difficult-to-feed powders like magnetic ones – e.g., Fe-based metallic glass powder – Fe56.04Co13.45Nb5.5B25. In this work, two algorithms – machine learning – Support Vector Machines (SVM), deep learning – Convolutional Neural Networks (CNN) – were evaluated for their ability to detect and classify the enumerated anomalies based on powder layer images. The SVM algorithm makes it possible to efficiently and quickly analyze the powder-spreading process. CNN, however, appears to be a more promising choice for the developed application, as they alleviate the need for complex image operations.
EN
Our research aims to reconstruct expert preferences regarding the visual attractiveness of furniture fronts made of pine wood using machine learning algorithms. A numerical experiment was performed using five machine learning algorithms of various paradigms. To find the answer to the question of what determines the expert’s decision, we determined the importance of variables for some machine learning models. For random forest and classification trees, it involves the overall reduction in node impurities resulting from variable splitting, while for neural networks it uses the Garson algorithm. Based on the numerical experiments we can conclude that the best results of expert decision reconstruction are provided by a neural network model. The expert’s decision is better reconstructed for more beautiful images. The decision for nice images is made based on the best 4 or 5 variables, while for ugly images many more features are important. Prettier images and those for which the expert’s decision is better reconstructed have fewer knots.
EN
Rapid development of online medical technologies raises questions about the security of the patient’s medical data.When patient records are encrypted and labeled with a watermark, they may be exchanged securely online. In order to avoid geometrical attacks aiming to steal the information, image quality must be maintained and patient data must be appropriately extracted from the encoded image. To ensure that watermarked images are more resistant to attacks (e.g. additive noise or geometric attacks), different watermarking methods have been invented in the past. Additive noise causes visual distortion and render the potentially harmful diseases more difficult to diagnose and analyze. Consequently, denoising is an important pre-processing method for obtaining superior outcomes in terms of clarity and noise reduction and allows to improve the quality of damaged medical images. Therefore, various publications have been studied to understand the denoising methods used to improve image quality. The findings indicate that deep learning and neural networks have recently contributed considerably to the advancement of image processing techniques. Consequently, a system has been created that makes use of machine learning to enhance the quality of damaged images and to facilitate the process of identifying specific diseases. Images, damaged in the course of an assault, are denoised using the suggested technique relying on a symmetric dilated convolution neural network. This improves the system’s resilience and establishes a secure environment for the exchange of data while maintaining secrecy.
7
Content available Robotic Mobile Holder (For CAR Dashboards)
EN
In the current smart tech world, there is an immense need of automating tasks and processes to avoid human intervention, save time and energy. Nowadays, mobile phones have become one of the essential things for human beings either to call someone, connect to the internet, while driving people need mobile phones to receive or make a call, use google maps to know the routes and many more. Normally in cars, mobile holders are placed on the dashboard to hold the mobile and the orientation of the phone needs to be changed according to the driver's convenience manually, but the driver may distract from driving while trying to access mobile phone which may lead to accidents. To solve this problem, an auto adjustable mobile holder is designed in such a way that it rotates according to the movement of the driver and also it can even alert the driver when he feels drowsiness. Image Processing is used to detect the movement of the driver which is then processed using LabVIEW software and NI myRIO hardware. NI Vision development module is used to perform face recognition and servo motors are used to rotate the holder in the required position. Simulation results show that the proposed system has achieved maximum accuracy in detecting faces, drowsiness and finding the position coordinates.
EN
Automatic car license plate recognition (LPR) is widely used nowadays. It involves plate localization in the image, character segmentation and optical character recognition. In this paper, a set of descriptors of image segments (characters) was proposed as well as a technique of multi-stage classification of letters and digits using cascade of neural network and several parallel Random Forest or classification tree or rule list classifiers. The proposed solution was applied to automated recognition of number plates which are composed of capital Latin letters and Arabic numerals. The paper presents an analysis of the accuracy of the obtained classifiers. The time needed to build the classifier and the time needed to classify characters using it are also presented.
EN
The article aims to study the multi-level segmentation process of images of arbitrary configuration and placement based on features of spatial connectivity. Existing image processing algorithms are analyzed, and their advantages and disadvantages are determined. A method of organizing the process of segmentation of multi-gradation halftone images is developed and an algorithm of actions according to the described method is given.
PL
Artykuł ma na celu zbadanie procesu wielopoziomowego segmentacji obrazów o dowolnej konfiguracji i rozmieszczeniu w oparciu o cechy łączności przestrzennej. Przeanalizowano istniejące algorytmy przetwarzania obrazu oraz określono ich zalety i wady. Opracowano metodę organizacji procesu segmentacji wielogradacyjnych obrazów półtonowych i przedstawiono algorytm działań zgodnie z opisaną metodą.
EN
Bone fractures break bone continuity. Impact or stress causes numerous bone fractures. Fracture misdiagnosis is the most frequent mistake in emergency rooms, resulting in treatment delays and permanent impairment. According to the Indian population studies, fractures are becoming more common. In the last three decades, there has been a growth of 480 000, and by 2022, it will surpass 600 000. Classifying X-rays may be challenging, particularly in an emergency room when one must act quickly. Deep learning techniques have recently become more popular for image categorization. Deep neural networks (DNNs) can classify images and solve challenging problems. This research aims to build and evaluate a deep learning system for fracture identification and bone fracture classification (BFC). This work proposes an image-processing system that can identify bone fractures using X-rays. Images from the dataset are pre-processed, enhanced, and extracted. Then, DNN classifiers ResNeXt101, InceptionResNetV2, Xception, and NASNetLarge separate the images into the ones with unfractured and fractured bones (normal, oblique, spiral, comminuted, impacted, transverse, and greenstick). The most accurate model is InceptionResNetV2, with an accuracy of 94.58%.
EN
Finger tapping is one of the standard tests for Parkinson's disease diagnosis performed to assess the motor function of patients' upper limbs. In clinical practice, the assessment of the patient's ability to perform the test is carried out visually and largely depends on the experience of clinicians. This article presents the results of research devoted to the objectification of this test. The methodology was based on the proposed measurement method consisting in frame processing of the video stream recorded during the test to determine the time series representing the distance between the index finger and the thumb. Analysis of the resulting signals was carried out in order to determine the characteristic features that were then used in the process of distinguishing patients with Parkinson's disease from healthy cases using methods of machine learning. The research was conducted with the participation of 21 patients with Parkinson's disease and 21 healthy subjects. The results indicate that it is possible to obtain the sensitivity and specificity of the proposed method at the level of approx. 80 %. However, the patients were in the so-called ON phase when symptoms are reduced due to medication, which was a much greater challenge compared to analyzing signals with clearly visible symptoms as reported in related works.
EN
Metal 3D printing is a modern manufacturing process that allows the production of geometrically complex structures from metallic powders of varying chemical composition. This paper shows the results of testing the powder feeding and distribution system of the developed 3D printer. The device using the SLM method (Selected Laser Melting) was developed by research team of WroclawTech and used in this investigation. The powder feeding and distribution system was tested using a vision system integrated into the printer control system. Thousands of tests performed made it possible to identify the reasons corresponding to incorrect powder distribution on the working field. In addition, a quality control algorithm was developed and implemented in the MatLab environment. Algorithms based on image analysis automatically identifies powder distributed in an unacceptable way. An 88% accuracy rate was achieved for identifying defects in all images within a dataset of 600 pictures, classified into following categories OK and NOK consisting of: recoater streaking, recoater hopping, super-elevation. The strength of the algorithm developed lies in its utilization of variations in shades of gray, rather than solely relying on the actual gray values. This approach grants the algorithm a certain degree of adaptability to changing lighting conditions.
EN
In this paper, the climate and environmental datasets were processed by the scripts of Generic Mapping Tools (GMT) and R to evaluate changes in climate parameters, vegetation patters and land cover types in Burkina Faso. Located in the southern Sahel zone, Burkina Faso experiences one of the most extreme climatic hazards in sub-saharan Africa varying from the extreme floods in Volta River Basin, to desertification and recurrent droughts.. The data include the TerraClimate dataset and satellite images Landsat 8-9 Operational Land Imager (OLI) and Thermal Infrared (TIRS) C2 L1. The dynamics of target climate characteristics of Burkina Faso was visualised for 2013-2022 using remote sensing data. To evaluate the environmental dynamics the TerraClimate data were used for visualizing key climate parameter: extreme temperatures, precipitation, soil moisture, downward surface shortwave radiation, vapour pressure deficit and anomaly. The Palmer Drought Severity Index (PDSI) was modelled over the study area to estimate soil water balance related to the soil moisture conditions as a prerequisites for vegetation growth. The land cover types were mapped using the k-means clustering by R. Two vegetation indices were computed to evaluate the changes in vegetation patterns over recent decade. These included the Normalized Difference Vegetation Index (NDVI) and the Soil-Adjusted Vegetation Index (SAVI) The scripts used for cartographic workflow are presented and discussed. This study contributes to the environmental mapping of Burkina Faso with aim to highlight the links between the climate processes and vegetation dynamics in West Africa.
PL
W tym referacie poruszamy problem wykrywania danych ukrytych steganograficznie w plikach JPEG. Zostały przedstawione najpopularniejsze algorytmy służące do ukrywania informacji w obrazach, a następnie zostały omówione algorytmy służące do ekstrakcji cech z obrazów cyfrowych. Pokazane zostały metody opisane w literaturze bazujące na ekstrakcji cech DCTR, GFR oraz PHARM oraz sieciach neuronowych w architekturze Convolution-Batch- Normalization-Dense. Zostało zaproponowane nowe rozwiązanie z wykorzystaniem prostej sieci neuronowej, przeprowadzone zostały badania dokładności oraz innych metryk dla najlepszej konfiguracji sieci.
EN
In this paper we deal with the problem of detection steganographically hidden data in JPEG files. The most popular algorithms for hiding information in images are presented and next we discussed algorithms for extracting features from digital images. We presented the methods described in the literature, which are based on the extraction of DCTR, GFR and PHARM features and using neural networks in the Convolution-Batch-Normalization-Dense scheme. A new solution with a simple neural network was proposed and tested.
15
Content available remote Visualization of bronze material structure in virtual reality
EN
This experimental study aims to design and apply procedures for visualizing a real object in a virtual reality environment. 3D reconstruction of the object by photogrammetry is the basis for further procedures of working with the 3D model. Attention is focused primarily on working with the bronze material and structure of the object. The experiment aims to achieve a high level of image quality in virtual reality. The text describes the characteristic properties of the material and structure, which is the subject of separate image processing in a digital 3D model. Furthermore, procedures for further processing the 3D model and modification of its attributes for export and import between the individual software used in this experiment are designed and applied. The 2D and 3D graphics methods are used for the final visual appearance of the object in virtual reality and tools for creating the original material of the real object.
PL
To eksperymentalne badanie ma na celu zaprojektowanie i zastosowanie procedur wizualizacji rzeczywistego obiektu w środowisku wirtualnej rzeczywistości. Rekonstrukcja obiektu 3D metodą fotogrametrii jest podstawą do dalszych procedur pracy z modelem 3D. Uwaga skupiona jest przede wszystkim na pracy z brązem i strukturą przedmiotu. Eksperyment ma na celu osiągnięcie wysokiego poziomu jakości obrazu w wirtualnej rzeczywistości. Tekst opisuje charakterystyczne właściwości materiału i struktury, która jest przedmiotem odrębnej obróbki obrazu w cyfrowym modelu 3D. Ponadto opracowano i zastosowano procedury dalszego przetwarzania modelu 3D i modyfikacji jego atrybutów w celu eksportu i importu pomiędzy poszczególnymi programami używanymi w tym eksperymencie. Metody graficzne 2D i 3D służą do ostatecznego wyglądu wizualnego obiektu w wirtualnej rzeczywistości oraz narzędzia do tworzenia oryginalnego materiału obiektu rzeczywistego.
16
Content available remote Parameters evaluation of cameras in embedded systems
EN
The article presents a comparison of micro cameras for video data acquisition. The tested cameras can be used in conjunction with embedded systems, in particular in the system for detecting mechanical damage of airport lamps. The work verified the compatibility of operation with microcomputers: Raspberry Pi 4B, Google Coral, NVIDIA Jetson Nano and NVIDIA Jetson Xavier AGX and cameras: Raspberry Pi Camera HD v2, Waveshare 16579, IMX477 and Logitech C922. Tests were performed under laboratory conditions based on an ISO 12233 standard test chart.
PL
W artykule przedstawiono porównanie mikrokamer do akwizycji danych wizyjnych. Testowane kamery mogą zostać użyte w połączeniu z systemami wbudowanymi, w szczególności w systemie do wykrywania uszkodzeń mechanicznych lamp lotniskowych. W pracy sprawdzono kompatybilność działania z mikrokomputerami: Raspberry Pi 4B, Google Coral, NVIDIA Jetson Nano i NVIDIA Jetson Xavier AGX oraz kamery: Raspberry Pi Camera HD v2, Waveshare 16579, IMX477 i Logitech C922. Testy przeprowadzono w warunkach laboratoryjnych, w oparciu o standardową tablicę testową ISO 12233.
17
Content available remote Możliwości przetwarzania sekwencji wizyjnych w systemach wbudowanych
PL
W artykule przedstawiono wyniki badań eksperymentalnych procesu segmentacji sekwencji wizyjnych z wykorzystaniem systemów wbudowanych. Przetestowano wydajność rozwiązań opartych o mikrokomputer Raspberry Pi 4B oraz platformę Nvidia Jetson Nano pod kątem możliwości ich implementacji w platformie pomiarowej do automatycznego badania jakości działania lamp lotniskowych. Porównano szybkość przetwarzania dla różnych rozdzielczości obrazu oraz wymagania związane z zasilaniem modułów.
EN
The article presents the results of experimental research on the video segmentation process using two different embedded systems. The performance of solutions based on the Raspberry Pi 4B microcomputer and the Nvidia Jetson Nano platform was tested for the possibility of their implementation in a measurement platform for automatic testing of the quality of airport lamps. The processing speed for different image resolutions and the module power requirements were compared.
18
PL
Artykuł przedstawia różne sposoby otrzymywania warstw aktywnych w organicznych ogniwach słonecznych oraz metody detekcji ich defektów strukturalnych. Przedstawiono metody optyczne, gdzie etapowo określane są defekty z różną dokładnością, wykorzystujące przetwarzanie zobrazowań w zakresie widzialnym oraz w zakresie termalnym.
EN
The article presents various methods of obtaining active layers in organic solar cells and methods of detecting their structural defects. Optical methods are presented, where defects are determined in stages with different accuracy, using image processing in the visible and thermal range.
19
EN
The article presents an overview of the thresholding algorithms. It compares the algorithms proposed by Pun, Kittler, Niblack, Huang, Rosenfeld, Remesh, Lloyd, Riddler, Otsu, Yanni, Kapur and Jawahar. Additionally, it was tested how the tuning of the Pun, Jawahar and Niblack methods affects the thresholding efficiency and proposed a combination of the Pun algorithm with a priori algorithm. All presented algorithms have been implemented and tested for effectiveness in detecting overhead lines.
PL
W artykule przedstawiono przegląd algorytmów progowania. Porównano w nim algorytmy zaproponowane przez Puna, Kittlera, Niblacka, Huanga, Rosenfelda, Remesha, Lloydaa, Riddlera, Otsu, Yanni, Kapura i Jawahara. Dodatkowo przetestowano, jak dostrajanie metod Puna, Jawahara i Niblacka wpływa na skuteczność progowania oraz zaproponowano połączenie algorytmu Puna z algorytmem a priori. Wszystkie przedstawione algorytmy zostały zaimplementowane i przetestowane pod kątem skuteczności w wykrywaniu linii napowietrznych
20
Content available remote Automatics detect and Shooter Robot based on object detection using camera
EN
Detection color and shape has been widely developed. The target detection and follower robot system has been developed by previous researchers, and in the military world there are still few who develop automatic shooting robots. From it researchers create a robot can detect and shoot targets automatic, where the camera is used to detect the target, while the navigation system uses the PID method. The robot works when it receives a command from the user to search for a predetermined target, the camera will capture, and image will processed in a mini PC to get conformity. After that, the robot will adjust the robot's position to the target, and robot moved closer to the target robot will stop and the system will shoot the target automatically. From the results of the research that has been obtained, the PID value settings that are most suitable for the system are the values of Kp 10, ki 0.9, and kd 0.5. The overall system test got a success rate of 83.3%, with the fastest time to find and shoot targets is 17 seconds. It is hoped that this research can help the military field in implementing an automatic target shooter system.
PL
Kolor i kształt wykrywania zostały szeroko rozwinięte. System robotów do wykrywania celów i śledzenia został opracowany przez poprzednich badaczy, a w świecie wojskowym wciąż niewiele osób opracowuje automatyczne roboty strzelające. Od niego naukowcy tworzą robota, który może wykrywać i strzelać do celów automatycznie, gdzie kamera służy do wykrywania celu, podczas gdy system nawigacji wykorzystuje metodę PID. Robot działa, gdy otrzyma polecenie od użytkownika, aby wyszukać z góry określony cel, kamera przechwyci, a obraz zostanie przetworzony na mini PC w celu uzyskania zgodności. Następnie robot dostosuje pozycję robota do celu, a robot zbliżony do celu zatrzyma się, a system automatycznie wystrzeli w cel. Z uzyskanych wyników badań wynika, że najbardziej odpowiednimi dla układu nastawami wartości PID są wartości Kp 10, ki 0,9 i kd 0,5. Ogólny test systemu uzyskał wynik 83,3%, a najkrótszy czas na znalezienie i strzelenie do celu to 17 sekund. Mamy nadzieję, że badania te mogą pomóc wojsku we wdrożeniu automatycznego systemu strzelania do celu.
first rewind previous Strona / 37 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.