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

Znaleziono wyników: 179

Liczba wyników na stronie
first rewind previous Strona / 9 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  image segmentation
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 9 next fast forward last
1
Content available remote Segmentation of aggregate and asphalt in photographic images of pavements
EN
Particle size distribution of aggregate in asphalt pavements is used for determining important characteristics like stiffness, durability, fatigue resistance, etc. Unfortunately, measuring this distribution requires a sieving process that cannot be done directly on the already mixed pavement. The use of digital image processing could facilitate this measurement, for which it is important to classify aggregate from asphalt in the image. This classification is difficult even for humans and much more for classical image segmentation algorithms. In this paper, an expert committee approach was used, including classical adaptive Otsu, k-means vector quantization over a set of 8 principal components obtained from 26 features, and a Gaussian mixture model whose parameters are estimated through the expectation-maximization algorithm. A novel cellular automata approach is used to coordinate these expert opinions. Finally, a simple heuristic is used to reduce sub- and over-segmentation. The segmentation results are comparable to those obtained by a human expert, while the sieve size of the segmented images corresponds very well with that obtained from the sieving process, validating the proposed method of segmentation. The results show that with the digital imaging procedure it was possible to detect particles with a size of 100 m with 90% of success with respect to time-consuming manual techniques. In addition, with these results it is possible to establish the homogeneity of the sample and the distribution of the particles within the asphalt mixture.
EN
In the framework of non-destructive evaluation (NDE), an accurate and precise characterization of defects is fundamental. This paper proposes a novel method for characterization of partial detachment of thermal barrier coatings from metallic surfaces, using the long pulsed thermography (LPT). There exist many applications, in which the LPT technique provides clear and intelligible thermograms. The introduced method comprises a series of post-processing operations of the thermal images. The purpose is to improve the linear fit of the cooling stage of the surface under investigation in the logarithmic scale. To this end, additional fit parameters are introduced. Such parameters, defined as damage classifiers, are represented as image maps, allowing for a straightforward localization of the defects. The defect size information provided by each classifier is, then, obtained by means of an automatic segmentation of the images. The main advantages of the proposed technique are the automaticity (due to the image segmentation procedures) and relatively limited uncertainties in the estimation of the defect size.
EN
The project aimedto develop and implement algorithms to diagnose the phase separation process based on digital images. The image processing techniques and various numerical methods for interpolation and integration were used to identify the process state. The swirl’s volume and diametersat its three different levelscan be determined on-line. A consistent diagnostic signal is produced and can be used by the control unit. The program was written in Python using the OpenCV library that allows the analysis of digital images. The article presents thedeveloped procedure that provides reliable results despite the poor quality of theinput source video stream. The complete procedure was described with the results’ presentation and discussionat each step.
PL
Celem projektu było opracowanie oraz implementacja algorytmów pozwalających diagnozować przebieg procesu separacji faz na podstawie obrazów cyfrowych. W kontekście identyfikacji stanu procesu wykorzystano techniki przetwarzania obrazów oraz metody numeryczne interpolacjioraz całkowanianumerycznego. Wyznaczane są charakterystyczne parametry wiru jak objętość oraz średnice na trzech różnych jego wysokościach. Zwracany spójny sygnał diagnostyczny może być dalej wykorzystany przez jednostkę sterującą. Program został napisany w języku Python z wykorzystaniem biblioteki OpenCV pozwalającej na przetwarzanie obrazów cyfrowych.W artykule zaprezentowano opracowaną procedurę, która dostarcza wiarygodnych wyników mimo słabej jakości obrazów wejściowych wynikającej ze złego oświetlenia sceny. Procedura została opisana wraz z prezentacją wyników i dyskusją nakażdym jej etapie.
EN
A magnetic anomaly map of an underwater area indicates the places where the distortion of a magnetic field has occurred. Through the interpretation procedures, a hydrographer can easily indicate the places where the ferromagnetic objects are, then calculate the level of each distortion – by the value of total anomaly – and initially, based on their own knowledge, try to classify the sources of distortion. Objects that induce micro anomaly changes (>30 nT) – like industrial infrastructure, such as pipelines and cables; to unintendingly located targets with ferromagnetic characteristics: wrecks (vessels, planes, cars), military mines, UXO, lost anchors and chains. Interpretation of such a map with the attempt to identify the source of magnetic field distortion, requires a specific knowledge as well as experience. In this article the author presents the research results of dimensioning and location of potential ferromagnetic underwater objects based on a magnetic anomaly map. For further consideration an anchor of buoyage system is taken into account. Geolocation of ferromagnetic sources, contours extraction and dimensioning algorithms of ferromagnetic targets have been carried out in Matlab software. The map of magnetic anomaly enhanced with extracted information was developed in ArcGIS. The analysis was carried out for the purpose of the dissertation thesis and the results are used in further research.
PL
Mapa anomalii magnetycznych obszaru podwodnego wskazuje miejsca, w których występuje zniekształcenie ziemskiego pola magnetycznego. Za pomocą procedur interpretacyjnych hydrograf może łatwo wskazać miejsca, w których znajdują się obiekty ferromagnetyczne, a następnie obliczyć poziom każdego zniekształcenia – według wartości całkowitej anomalii – i na podstawie własnej wiedzy spróbować sklasyfikować źródła zniekształceń. Obiekty, które indukują zniekształcenie pola magnetycznego na obszarach wodnych, mogą być różne. Te wywołujące zmiany pola magnetycznego (anomalia >30 nT) to między innymi infrastruktura przemysłowa, np.: rurociągi i kable, a także nieumyślnie zlokalizowane cele o charakterystyce ferromagnetycznej: wraki (statków, samolotów, samochodów), miny wojskowe, niewybuchy, kotwice i łańcuchy statków. Interpretacja takiej mapy w celu zidentyfikowania źródła zniekształcenia pola magnetycznego wymaga specjalistycznej wiedzy i doświadczenia. Całkowita wartość anomalii magnetycznej określa wielkość poziomu ferromagnetyzmu obiektu, a wymiar powierzchni objętej anomalią umożliwia geolokalizację celu i ustalenie jego wymiarów. W artykule autorzy przedstawiają wyniki badań wymiarowania i lokalizacji potencjalnych ferromagnetycznych podwodnych obiektów na podstawie mapy anomalii magnetycznych. Przeanalizowano anomalię magnetyczną spowodowaną przez kotwicę oznakowania nawigacyjnego. Geolokalizacja źródeł ferromagnetycznych, ekstrakcja ich konturów i algorytmy wymiarowania celów ferromagnetycznych zostały przeprowadzone za pomocą oprogramowania Matlab. Porównano i podsumowano wyniki działania różnych filtrów stosowanych do przetwarzania obrazów. Mapa anomalii magnetycznej wzbogacona o wyodrębnione informacje została opracowana w ArcGIS. Analiza została przeprowadzona na potrzeby pracy doktorskiej, a jej wyniki wykorzystano w dalszych badaniach
5
Content available remote Speckle noise reduction and image segmentation based on a modified mean filter
EN
Image segmentation is an essential process in many fields involving digital images. In gen-eral, segmentation is the process of dividing the image into objects and background image.Image segmentation is an important step in the object detection process. It becomes morecritical if a given image is corrupted by noise. Most digital images are corrupted by noisessuch as salt and pepper noise, Gaussian noise, Poisson noise, speckle noise, etc. Specklenoise is a multiplicative noise that affects pixels in a gray-scale image, and mainly occursin low level luminance images such as Synthetic Aperture Radar (SAR) images and Mag-netic Resonance Image (MRI) images. Image enhancement is an essential task to reducespecklenoise prior to performing further image processing such as object detection, imagesegmentation, edge detection, etc. Here, we propose a neighborhood-based algorithm toreduce speckle noise in gray-scale images. The main aim of the noise reduction technique isto segment the noisy image. So that the proposed algorithm applies some luminance to theoriginal image. The proposed technique performs well at maximum noise variance. Finally,the segmentation process is done by the modified mean filter. The proposed technique hasthree phases. In phase 1, the speckle noise is reduced and the contrast adjustment is made.In phase 2, the segmentation of the enhanced image is processed. Finally, in phase 3, theisolated pixels in the segmented image are eliminated and the final segmented image isgenerated. This technique does not require any threshold value to segment the image; itwill be automatically calculated based on the mean value.
EN
Segmentation of retinal layers is a vital and important step in computerized processing and the study of retinal Optical Coherence Tomography (OCT) images. However, automatic segmentation of retinal layers is challenging due to the presence of noise, widely varying reflectivity of image components, variations in morphology and alignment of layers in the presence of retinal diseases. In this paper, we propose a Fully Convolutional Network (FCN) termed as DelNet based on a deep ensemble learning approach to selectively segment retinal layers from OCT scans. The proposed model is tested on a publicly available DUKE DME dataset. Comparative analysis with other state-of-the-art methods on a benchmark dataset shows that the performance of DelNet is superior to other methods.
7
EN
Accurate segmentation of brain tissues in magnetic resonance imaging (MRI) data plays critical role in the clinical diagnostic and treatment planning. The presence of noise and artifacts in MRI data degrades the performance of segmentation algorithms. In this view, the present study proposes a complete unsupervised clustering based multi-objective modified fuzzy c-mean (MOFCM) segmentation algorithm, which inculcates multi-objective antlion optimization (MOALO) to minimize the cluster compactness and fuzzy hyper-volume fitness functions. The output segmented image corresponds to minimum value of partition entropy in the obtained solution set. The present study integrates proposed MOFCM with a new cluster number validity index, which allows user not to provide number of segments in image as an input. The proposed MOFCM algorithm is extensively validated on seventy two synthetic images corrupted with different levels of Gaussian, Speckle and Rician noises, forty simulated BrainWeb MRI images suffered from noise and inhomogeneity, and 10 real IBSR MRI dataset of images. The results are compared with existing popular clustering based algorithms, and supervised deep learning based algorithms, i.e. UNet, SegNet and Quick- NAT. The proposed MOFCM algorithm demonstrate the superior segmentation performance in comparison to popular FCM based clustering algorithms, SegNet and UNet, whereas the segmentation results of proposed MOFCM are at par with QuickNAT.
8
Content available remote Multi-path convolutional neural network in fundus segmentation of blood vessels
EN
There is a close correlation between retinal vascular status and physical diseases such as eye lesions. Retinal fundus images are an important basis for diagnosing diseases such as diabetes, glaucoma, hypertension, coronary heart disease, etc. Because the thickness of the retinal blood vessels is different, the minimum diameter is only one or two pixels wide, so obtaining accurate measurement results becomes critical and challenging. In this paper, we propose a new method of retinal blood vessel segmentation that is based on a multi-path convolutional neural network, which can be used for computer-based clinical medical image analysis. First, a low-frequency image characterizing the overall characteristics of the retinal blood vessel image and a high-frequency image characterizing the local detailed features are respectively obtained by using a Gaussian low-pass filter and a Gaussian high-pass filter. Then a feature extraction path is constructed for the characteristics of the low- and high-frequency images, respectively. Finally, according to the response results of the low-frequency feature extraction path and the high-frequency feature extraction path, the whole blood vessel perception and local feature information fusion coding are realized, and the final blood vessel segmentation map is obtained. The performance of this method is evaluated and tested by DRIVE and CHASE_DB1. In the experimental results of the DRIVE database, the evaluation indexes accuracy (Acc), sensitivity (SE), and specificity (SP) are 0.9580, 0.8639, and 0.9665, respectively, and the evaluation indexes Acc, SE, and SP of the CHASE_DB1 database are 0.9601, 0.8778, and 0.9680, respectively. In addition, the method proposed in this paper could effectively suppress noise, ensure continuity after blood vessel segmentation, and provide a feasible new idea for intelligent visual perception of medical images.
EN
For the Convolutional Neural Networks (CNNs) applied in the intelligent diagnosis of gastric cancer, existing methods mostly focus on individual characteristics or network frameworks without a policy to depict the integral information. Mainly, conditional random field (CRF), an efficient and stable algorithm for analyzing images containing complicated contents, can characterize spatial relation in images. In this paper, a novel hierarchical conditional random field (HCRF) based gastric histopathology image segmentation (GHIS) method is proposed, which can automatically localize abnormal (cancer) regions in gastric histopathology images obtained by an optical microscope to assist histopathologists in medical work. This HCRF model is built up with higher order potentials, including pixel-level and patch-level potentials, and graph-based post-processing is applied to further improve its segmentation performance. Especially, a CNN is trained to build up the pixel-level potentials and another three CNNs are fine-tuned to build up the patch-level potentials for sufficient spatial segmentation information. In the experiment, a hematoxylin and eosin (H&E) stained gastric histopathological dataset with 560 abnormal images are divided into training, validation and test sets with a ratio of 1 : 1 :2. Finally, segmentation accuracy, recall and specificity of 78.91%, 65.59%, and 81.33% are achieved on the test set. Our HCRF model demonstrates high segmentation performance and shows its effectiveness and future potential in the GHIS field.
EN
Leukemia is an abnormal proliferation of leukocytes in the bone marrow and blood and it is usually diagnosed by the pathologists by observing the blood smear under a microscope. The count of various cells and their morphological features are used by the pathologists to identify and classify leukemia. An abnormal increase in the count of immature leukocytes along with a reduced count of other blood cells may be an indication of leukemia. The Pathologist may then recommend for bone marrow examination to confirm and identify the specific type of leukemia. These conventional methods are time consuming and may be affected by the skill and expertise of the medical professionals involved in the diagnostic procedures. Image processing based methods can be used to analyze the microscopic smear images to detect the incidence of leukemia automatically and quickly. Image segmentation is one of the very important tasks in processing and analyzing medical images. In the proposed paper an attempt has been made to review the available works in the area of medical image processing of blood smear images, highlighting automated detection of leukemia. The available works in the related area are reviewed based on the segmentation method used. It is learnt that even though there are many studies for detection of acute leukemia only a very few studies are there for the detection of chronic leukemia. There are a few related review studies available in the literature but, none of the works classify the previous studies based on the segmentation method used.
EN
The aim of the study was to create an accurate method of automated subcutaneous (SAT) and visceral (VAT) adipose tissue detection basing on three-dimensional (3D) computed tomography (CT) scans. One hundred and forty abdominal CT examinations were analysed. An algorithm for automated detection of SAT and VAT consisted of following steps: thresholding of an analysed image, detection of a patient's body region, separation of SAT and VAT. The algorithm was sequentially applied to each 2D axial slice of a 3D examination. To assess the accuracy of the proposed method, automated and manual segmentations (performed by two readers) of SAT and VAT were compared using Dice similarity coefficient (DSC) and average Hausdorff distance (AHD). Mean DSC was equal to 99.6% ± 0.4% for SAT and 99.6% ± 0.5% for VAT, which was equal to DSC obtained for comparison between both readers. In 90% of cases DSC was equal or above 99.0% and the minimal DSC was 97.6%. AHD equalled to 0.04 ± 0.06 for SAT and 0.13 ± 0.23 for VAT (automated vs. manual segmentations), while AHD for comparison of two manual segmentations was 0.03 ± 0.07 for SAT and 0.09 ± 0.20 for VAT. The processing time for a single slice was 0.16 s for an automated segmentation and 510 min for a manual segmen- tation. The processing time of an entire 3D stack (around 40 2D slices) was on average 6.5 s. Our algorithm for the automated detection of SAT and VAT on 3D CT scans has the same accuracy as manual segmentation and performs equally well for both adipose tissue compartments.
12
Content available remote Review of Printed Fabric Pattern Segmentation Analysis and Application
EN
Image processing of digital images is one of the essential categories of image transformation in the theory and practice of digital pattern analysis and computer vision. Automated pattern recognition systems are much needed in the textile industry more importantly when the quality control of products is a significant problem. The printed fabric pattern segmentation procedure is carried out since human interaction proves to be unsatisfactory and costly. Hence, to reduce the cost and wastage of time, automatic segmentation and pattern recognition are required. Several robust and efficient segmentation algorithms are established for pattern recognition. In this paper, different automated methods are presented to segregate printed patterns from textiles fabric. This has become necessary because quality product devoid of any disturbances is the ultimate aim of the textile printing industry.
PL
Stworzenie nowej metody estymacji map głębi przeznaczonej dla systemów telewizji swobodnego widzenia jest głównym celem przedstawionych badań. W telewizji swobodnego punktu widzenia możliwości widza są rozszerzone poprzez możliwość kontroli aktualnie oglądanego przez niego punktu widzenia sceny. Nowa metoda estymacji map głębi zaproponowana przez autora składa się z trzech części: przestrzennie spójnej estymacji map głębi opartej na segmentacji widoków, metodzie zwiększenia spójności czasowej map głębi zmniejszającej złożoność obliczeniową estymacji oraz nową metodę zrównoleglania procesu optymalizacji opartego na wykorzystaniu grafów.
EN
The development of a novel depth estimation method for free viewpoint television systems is the main goal of presented research. In free viewpoint television the functionalities offered to a viewer are extended by the possibility of controlling the displayed viewpoint of a scene. The novel method for depth estimation proposed by the author of the dissertation consists of three parts: the interview consistent segment-based depth estimation method, the temporal consistency enhancement that simultaneously increases temporal consistency of depth maps and reduces the complexity of estimation, and a new method of parallelisation for graph based depth estimation methods.
EN
Image segmentation is a typical operation in many image analysis and computer vision applications. However, hyperspectral image segmentation is a field which have not been fully investigated. In this study an analogue-digital image segmentation technique is presented. The system uses an acousto-optic tuneable filter, and a CCD camera to capture hyperspectral images that are stored in a digital grey scale format. The dataset was built considering several objects with remarkable differences in the reflectance and brightness components. In addition, the work presents a semi-supervised segmentation technique to deal with the complex problem of hyperspectral image segmentation, with its corresponding quantitative and qualitative evaluation. Particularly, the developed acousto-optic system is capable to acquire 120 frames through the whole visible light spectrum. Moreover, the analysis of the spectral images of a given object enables its segmentation using a simple subtraction operation. Experimental results showed that it is possible to segment any region of interest with a good performance rate by using the proposed analogue-digital segmentation technique.
15
Content available remote BCT Boost Segmentation with U-net in TensorFlow
EN
In this paper we present a new segmentation method meant for boost area that remains after removing the tumour using BCT (breast conserving therapy). The selected area is a region on which radiation treatment will later be made. Consequently, an inaccurate designation of this region can result in a treatment missing its target or focusing on healthy breast tissue that otherwise could be spared. Needless to say that exact indication of boost area is an extremely important aspect of the entire medical procedure, where a better definition can lead to optimizing of the coverage of the target volume and, in result, can save normal breast tissue. Precise definition of this area has a potential to both improve the local control of the disease and to ensure better cosmetic outcome for the patient. In our approach we use U-net along with Keras and TensorFlow systems to tailor a precise solution for the indication of the boost area. During the training process we utilize a set of CT images, where each of them came with a contour assigned by an expert. We wanted to achieve a segmentation result as close to given contour as possible. With a rather small initial data set we used data augmentation techniques to increase the number of training examples, while the final outcomes were evaluated according to their similarity to the ones produced by experts, by calculating the mean square error and the structural similarity index (SSIM).
EN
This article presents a computer vision method for measuring the geometrical parameters of slub yarn based on yarn sequence images captured from a moving slub yarn. An image segmentation method proposed by our earlier work was applied to segment sequence slub yarn images to obtain overlapping diameter data. Then an image stitching method was proposed to remove the overlapped data based on the normalised cross correlation (NCC) method. In order to detect the geometrical parameters of slub yarn, the frequency histogram, curve fitting , and spectrogram methods were adopted to analyse the sequence diameter data obtained. Four kinds of slub yarn with different geometrical parameters were tested using the method proposed and Uster method. The experimental results show that the detection results for slub amplitude, slub length, slub distance, and slub period obtained using the method proposed were consistent with the set values and Uster results.
PL
W artykule przedstawiono komputerową metodę pomiaru parametrów geometrycznych przędzy fantazyjnej na podstawie sekwencjonowania obrazów. Metoda segmentacji obrazu zaproponowana we wcześniejszej pracy została zastosowana do obrazów przędzy fantazyjnej w celu uzyskania danych dotyczących pomiarów średnicy. Następnie, w celu usunięcia nakładających się danych, zaproponowano metodę obróbki obrazu opartą o znormalizowaną metodę korelacji krzyżowej (NCC). W celu wykrycia parametrów geometrycznych przędzy fantazyjnej zastosowano histogram częstotliwości oraz dopasowanie krzywej i metody spektrogramowe do analizy uzyskanych danych. Za pomocą proponowanej metody i metody Uster przeanalizowano cztery rodzaje przędz fantazyjnych o różnych parametrach geometrycznych. Wyniki eksperymentalne wykazały, że wyniki detekcji amplitudy, długości, odległości i okresu wzgrubień uzyskane przy użyciu proponowanej metody były zgodne z wartościami zadanymi i wynikami Uster.
EN
In the present work, the performance assessment of despeckle filtering algorithms has been carried out for (α) noise reduction in breast ultrasound images and (b) segmentation of benign and malignant tumours from breast ultrasound images. The despeckle filtering algorithms are broadly classified into eight categories namely local statistics based filters, fuzzy filters, Fourier filters, multiscale filters, non-linear iterative filters, total variation filters, non-local mean filters and hybrid filters. Total 100 breast ultrasound images (40 benign and 60 malignant) are processed using 42 despeckle filtering algorithms. A despeckling filter is considered to be appropriate if it preserves edges and features/structures of the image. Edge preservation capability of a despeckling filter is measured by beta metric (β) and feature/structure preservation capability is quantified using image quality index (IQI). It is observed that out of 42 filters, six filters namely Lee Sigma, FI, FB, HFB, BayesShrink and DPAD yield more clinically acceptable images in terms of edge and feature/structure preservation. The qualitative assessment of these images has been done on the basis of grades provided by the experienced participating radiologist. The pre-processed images are then fed to a segmentation module for segmenting the benign or malignant tumours from ultrasound images. The performance assessment of segmentation algorithm has been done quantitatively using the Jaccard index. The results of both quantitative and qualitative assessment by the radiologist indicate that the DPAD despeckle filtering algorithm yields more clinically acceptable images and results in better segmentation of benign and malignant tumours from breast ultrasound images.
19
Content available remote A hybrid method for blood vessel segmentation in images
EN
In the last years, image processing has been an important tool for health care. The analysis of retinal vessel images has become crucial to achieving a better diagnosis and treatment for several cardiovascular and ophthalmological deceases. Therefore, an automatic and accurate procedure for retinal vessel and optic disc segmentation is essential for illness detection. This task is extremely hard and time-consuming, often requiring the assistance of human experts with a high degree of professional skills. Several retinal vessel segmentation methods have been developed with satisfactory results. Nevertheless, most of such techniques present a poor performance mainly due to the complex structure of vessels in retinal images. In this paper, an accurate methodology for retinal vessel and optic disc segmentation is presented. The proposed scheme combines two different techniques: the Lateral Inhibition (LI) and the Differential Evolution (DE). The LI scheme produces a new image with enhanced contrast between the background and retinal vessels. Then, the DE algorithm is used to obtain the appropriate threshold values through the minimization of the cross-entropy function from the enhanced image. To evaluate the performance of the proposed approach, several experiments over images extracted from STARE, DRIVE, and DRISHTI-GS databases have been conducted. Simulation results demonstrate a high performance of the proposed scheme in comparison with similar methods reported in the literature.
EN
Over the last few years, deep learning has proven to be a great solution to many problems, such as image or text classification. Recently, deep learning-based solutions have outperformed humans on selected benchmark datasets, yielding a promising future for scientific and real-world applications. Training of deep learning models requires vast amounts of high quality data to achieve such supreme performance. In real-world scenarios, obtaining a large, coherent, and properly labeled dataset is a challenging task. This is especially true in medical applications, where high-quality data and annotations are scarce and the number of expert annotators is limited. In this paper, we investigate the impact of corrupted ground-truth masks on the performance of a neural network for a brain tumor segmentation task. Our findings suggest that a) the performance degrades about 8% less than it could be expected from simulations, b) a neural network learns the simulated biases of annotators, c) biases can be partially mitigated by using an inversely-biased dice loss function.
first rewind previous Strona / 9 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.