Wyniki wyszukiwania - BazTech

1

Fast Segmentation of Convex Cyst-like Structures in Gelatin Soft Tissue Phantoms under Ultrasound Imaging with Artifacts and Limited Training Samples

Drozd Dalia, Ciszkiewicz Adam

Advances in Science and Technology. Research Journal

|

2024

|

Vol. 18, no 4

89--96

EN

Ultrasound imaging is common for surgical training and development of medical robotics systems. Recent advancements in surgical training often utilize soft-tissue phantoms based on gelatin, with additional objects inserted to represent different, typically fluid-based pathologies. Segmenting these objects from the images is an important step in the development of training and robotic systems. The current study proposes a simple and fast algorithm for segmenting convex cyst-like structures from phantoms under very low training sample scenarios. The algorithm is based on a custom two-step thresholding procedure with additional post-processing with two trainable parameters. Two large phantoms with convex cysts are created and used to train the algorithm and evaluate its performance. The train/test procedure are repeated 60 times with different dataset splits and prove the viability of the solution with only 4 training images. The DICE coefficients were on average at 0.92, while in the best cases exceeded 0.95, all with fast performance in single-thread operation. The algorithm might be useful for development of surgical training systems and medical robotic systems in general.

2

Comparison of thresholding algorithms for automatic overhead line detection procedure

Kowalski Paweł, Smyka Robert

Przegląd Elektrotechniczny

|

2022

|

R. 98, nr 3

149--155

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

3

Analyses of skin lesion areas after thresholding

Michalska Magdalena

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2020

|

T. 10, nr 3

9--12

EN

Melanoma is one of the fastest spreading cancers.The aim of the article is to segment the skin lesionsfrom human skin dermatoscopic images covered by melanoma. Threshold segmentation was used, which allows a single skin lesionto be analyzed. Itshows the four areas of each based on their color. The created software monitors the border of skin lesion areas.Segmentation and analysis of the resulting images with different areas of skin change was carried out in the Matlab software.

PL

Czerniak to jeden z najszybciej rozprzestrzeniających się nowotworów. Celem artykułu jest segmentacja zmiany skórnej z obrazów dermatoskopowych ludzkiej skóry objętych czerniakiem. Użyto segmentacj przez progowanie, która pozwala na analizę pojedyńczejzmiany skórnej. Ukazuje cztery obszary każdej z nich w oparciu o ich barwę. Stworzone oprogramowanie monitoruje granicę obszarów zmiany skórnej. Segmentacjai analiza powstałych obrazów z różnymi obszarami zmiany skórnej została przeprowadzona w środowisku Matlab.

4

Termowizyjna detekcja pieszych z użyciem segmentacji obrazu poprzez progowanie

Piniarski K., Pawłowski P

Elektronika : konstrukcje, technologie, zastosowania

|

2018

|

Vol. 59, nr 4

13--18

PL

W artykule zaprezentowano procedurę detekcji pieszych na obrazach termowizyjnych z użyciem udoskonalonych technik segmentacji obrazów z przeznaczeniem do samochodowych systemów widzenia nocnego. Na etapie segmentacji obrazu zaproponowano technikę podwójnego progowania, technikę rozszerzania obszarów zainteresowań oraz dodatkowe etapy filtracji względem proporcji boków, filtracji perspektywicznej oraz filtracji obszarów homogenicznych. Zaproponowane rozwiązania przetestowano na bazie nagrań termowizyjnych CVC-14. Wyniki pokazały, że zaproponowane techniki progowania z rozszerzaniem obszarów zainteresowań istotnie poprawiają wskaźnik chybienia (z 41,5% do 4,1%), a ograniczenie liczby kandydatów do dalszego przetwarzania poprzez filtrację pozwoliło na pracę algorytmu w czasie rzeczywistym (szybkość przetwarzania do 33 klatek na sekundę) z dokładnością detekcji na poziomie najnowszych rozwiązań występujących w literaturze.

EN

This paper presents a procedure for detection of pedestrians in thermal images using improved image segmentation techniques with application to the car night vision systems. Especially the image segmentation stage was improved by several original solutions: a double thresholding technique, a region expanding techniques and additional filtering steps with respect to the area of candidates, perspective filtering and the filtering of homogenous regions. All proposed solutions were tested with the CVC-14 pedestrian thermal dataset. The results showed that the proposed thresholding techniques with the region enlargement significantly improve the miss rate (from 41.5% to 4.1%). Additional filtering reduces the number of candidates for further processing and allows the algorithm to work in the real time (processing speed up to 33 frames per second) with the accuracy of detection comparable to the other state-of-the-art solutions.

5

Brain abnormality detection using template matching

Praveen G. B., Agrawal A., Pareek S., Prince A.

Bio-Algorithms and Med-Systems

|

2018

|

Vol. 14, no. 4

art. no. 20180029

EN

Magnetic resonance imaging (MRI) is a widely used imaging modality to evaluate brain disorders. MRI generates huge volumes of data, which consist of a sequence of scans taken at different instances of time. As the presence of brain disorders has to be evaluated on all magnetic resonance (MR) sequences, manual brain disorder detection becomes a tedious process and is prone to inter- and intra-rater errors. A technique for detecting abnormalities in brain MRI using template matching is proposed. Bias filed correction is performed on volumetric scans using N4ITK filter, followed by volumetric registration. Normalized cross-correlation template matching is used for image registration taking into account, the rotation and scaling operations. A template of abnormality is selected which is then matched in the volumetric scans, if found, the corresponding image is retrieved. Post-processing of the retrieved images is performed by the thresholding operation; the coordinates and area of the abnormality are reported. The experiments are carried out on the glioma dataset obtained from Brain Tumor Segmentation Challenge 2013 database (BRATS 2013). Glioma dataset consisted of MR scans of 30 real glioma patients and 50 simulated glioma patients. NVIDIA Compute Unified Device Architecture framework is employed in this paper, and it is found that the detection speed using graphics processing unit is almost four times faster than using only central processing unit. The average Dice and Jaccard coefficients for a wide range of trials are found to be 0.91 and 0.83, respectively.

6

Fast, accurate and robust retinal vessel segmentation system

Jiang Z., Yepez J., An S., Ko S.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 3

412--421

EN

The accurate segmentation of the retinal vessel tree has become the prerequisite step for automatic ophthalmological and cardiovascular diagnosis systems. Aside from accuracy, robustness and processing speed are also considered crucial for medical purposes. In order to meet those requirements, this work presents a novel approach to extract blood vessels from the retinal fundus, by using morphology-based global thresholding to draw the retinal venule structure and centerline detection method for capillaries. The proposed system is tested on DRIVE and STARE databases and has an average accuracy of 95.88% for single-database test and 95.27% for the cross-database test. Meanwhile, the system is designed to minimize the computing complexity and processes multiple independent procedures in parallel, thus having an execution time of 1.677 s per image on CPU platform.

7

Object Motion estimation using edge detection and background subtraction with block matching algorithm

Thapliyal Shardul, Pundir Yogendra Pratap, Bahuguna Arun Shekhar, Semwal Sunil

Annals of Computer Science and Information Systems

|

2017

|

Vol. 10

345--348

EN

Detection of an object motion is the growing research field of image processing which revealed the several applications. Several techniques (including the proposed one) are discussed so far in literatures. In this paper the edge detection and frame differencing also known as background subtraction technique with block matching algorithm has been implemented to detect the object motion. The object taken for experimentation is arbitrary having no fixed shape and size. The MATLAB output result showing the practicability of the both algorithms.

8

Applying chaotic imperialist competitive algorithm for multi-level image thresholding based on Kapur's entropy

Nejad M. R, Fartash M.

Advances in Science and Technology. Research Journal

|

2016

|

Vol. 10, nr 29

125--131

EN

Segmentation is one of the most important operations in image processing and computer vision. Normally, all image processing and computer vision applications are related to segmentation as a pre-processing phase. Image thresholding is one of the most useful methods for image segmentation. Various methods have been represented for image thresholding. One method is Kapur thresholding, which is based on maximizing entropy criterion. In this study, a new meta-heuristic algorithm based on imperialist competition algorithm was proposed for multi-level thresholding based on Kapur's entropy. Also, imperialist competitive algorithm is combined with chaotic functions to enhance search potency in problem space. The results of the proposed method have been compared with particle optimization algorithm and genetic algorithm. The findings revealed that the proposed method was superior to other methods.

9

Cross-Entropy Based Image Thresholding

Malik M., Spurek P., Tabor J.

Schedae Informaticae

|

2015

|

Vol. 24

21--29

EN

This paper presents a novel global thresholding algorithm for the binarization of documents and gray-scale images using Cross-Entropy Clustering. In the first step, a gray-level histogram is constructed, and the Gaussian densities are fitted. The thresholds are then determined as the cross-points of the Gaussian densities. This approach automatically detects the number of components (the upper limit of Gaussian densities is required).

10

Zastosowanie metody chan-vese w segmentacji obrazów medycznych

Prokop P.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2015

|

nr 4

32--37

PL

W artykule przedstawiono problem wyznaczania krawędzi obiektów zamkniętych w obrazach medycznych CT, które będą podlegały dalszej analizie, na potrzeby diagnostyki medycznej. Zastosowanie przekształcenia, które wprowadza progowanie, pozwala na wyeliminowanie pikseli prezentujących obiekty dla tkanek, które nie podlegają dalszej analizie. Podejście to pozwoliło na wyostrzenie krawędzi obiektów prezentujących tkanki miękkie. Porównano sposób wykrycia krawędzi tkanek miękkich, dla obrazu pierwotnego i przetworzonego za pomocą przekształcenia, z zastosowaniem metody Chan-Vese. Wyostrzenie krawędzi obrazu poprawiło dokładność wykrywania obiektów prezentujących tkanki miękkie.

EN

The article presents the problem of determining the edges of objects enclosed in a medical CT images, which will be subject to further analysis, for the purpose of medical diagnosis. The use of a transformation which introduces two-point thresholding, eliminates presenting pixels of objects for tissues that are not a subject to further analysis. This approach allowed us to sharpen the edges of objects presenting soft tissue. A way to detect the edge of the soft tissue was compared for the original image and processed one using the transformation using the method of Chan-Vese. Sharpening of edges of the image have improved the accuracy of detection of objects presenting the soft tissue.

11

Optimization of radiogram thresholding procedure

Baniukiewicz P.

Przegląd Spawalnictwa

|

2013

|

R. 85, nr 12

29--31

EN

This study deals with the automated segmentation of radiographic pictures, which is an important task in the process of automatic weld defect recognition. Generally, the process of radiogram binarisation is controlled by several parameters, the selection of which is a very demanding task that strongly influences the overall results. This paper presents an algorithm for an automatic selection thresholding method as well as its parameters using genetic programming techniques. The proposed method could be applied as part of the industrial process of automatic radiogram analysis.

PL

Praca porusza zagadnienia związane z procesem automatycznej obróbki i analizy cyfrowych zdjęć radiograficznych połączeń spawanych. W pracy zaprezentowano metodę doboru parametrów progowania zdjęć radiograficznych celem ekstrakcji obiektów – potencjalnych niezgodności spawalniczych. Dobór optymalnych parametrów procedury progowania dokonywany jest za pomocą techniki programowania genetycznego.

12

Performance comparison of wavelet thresholding techniques on weak ECG signal denoising

Üstündağ M., Şengür A., Gökbulut M., Ata F.

Przegląd Elektrotechniczny

|

2013

|

R. 89, nr 5

63-66

EN

The Electrocardiogram (ECG) signal is a biological non-stationary signal which contains important information about rhythms of heart. ECG signals can be buried by various types of noise. These types can be electrode movement, strong electromagnetic effect and muscle noise. Noisy ECG signal has been denoised using signal processing. This paper presents a weak ECG signal denoising method based on intervaldependent thresholds of wavelet analysis. Several experiments were conducted to show the effectiveness of the interval-dependent thresholding method and compared the results with the soft and hard wavelet thresholding methods for denoising. The results are evaluated by calculating the root mean square error and the correlation coefficient.

PL

W artykule przedstawiono metodę odszumiania sygnałów elektrokardiografu w oparciu o analizę falkową. W rozwiązaniu zastosowano progowanie przedziałowo-zależne. Na podstawie poczynionych eksperymentów oraz wyznaczonych wartości RMS błędu i współczynnika korelacji wykazano jego skuteczność. Dodatkowo dokonano porównania otrzymanych wyników z działaniem metod miękkiego i twardego progowania falkowego.

13

A comparison of Differential Evolution, Particle Swarm Optimization, Artificial Bee Colony and Cuckoo Search for Multilevel thresholding

Kumar S., Pant M., Kumar R., Amiya A.

Computer Methods in Materials Science

|

2013

|

Vol. 13, No. 1

135--140

EN

The present study deals with the image segmentation of waste wood material using some popular nature inspired metaheuristics like: Differential Evolution (DE), Particle Swarm Optimization(PSO) Artificial bee Colony (ABC) and Cuckoo Search (CS). Otsu’s between class-variance and Kapur’s maximum entropy techniques are used as fitness functions. Experiments have been performed on various images and numerical results are compared. It is observed that in some cases Otsu method is giving the same performance as DE, PSO, ABC and CS. But when class size increases DE shows better results in comparison to others.

PL

Przedstawione badania dotyczą segmentacji obrazów odpadów drewna przy użyciu popularnych algorytmów inspirowanych naturą, takich jak: metoda ewolucji różnicowej (DE), metoda roju cząstek (PSO), algorytmu pszczelego (ABC) oraz algorytmu kukułki (CS). Jako funkcję celu wykorzystano wariancję międzyklasową Otsu oraz zasadę maksymalnej entropii. Porównując wyniki otrzymane dla różnych obrazów, zaobserwowano, że w niektórych przypadkach metoda Otsu wykazuje taką samą wydajność jak DE, PSO, ABC i CS. Jednak przy wzroście liczby klas wyniki otrzymane metodą DE są lepsze niż otrzymane pozostałymi metodami.

14

Method of Skeletal System Modelling

Olszewski H., Wojnicz W., Wittbrodt E.

Archive of Mechanical Engineering

|

2013

|

Vol. LX, nr 3

335--346

EN

An original method of skeletal system modelling is presented in detail. Using DICOM images obtained from CT and PET tests, shell models of nine bones were created (humerus, radius, ulna, scapula, clavicle, femur, tibia, fibula, pelvis). Two methods of bone behaviour are also proposed, the first method treating the bone as a solid structure and the second method treating the bone as a complex porous structure. The behaviour of model parts is numerically examined by using the finite element method.

PL

W artykule opisano autorską metodę modelowania układu szkieletowego. Stosując zdjęcia DICOM otrzymane z badania CT i PET, utworzono dziewięć modeli powłokowych kości (kości ramiennej, kości promieniowej, kości łokciowej, łopatki, obojczyka, kości udowej, kości piszczelowej, kości strzałkowej i miednicy). Zaproponowano dwie metody modelowania zachowania kości. Zgodnie z pierwsza metoda kość jest traktowana jako bryła jednorodna, zgodnie z druga metoda - jako złożona struktura porowata. Zachowanie składowych części modelu zostało numerycznie przebadane, stosując metodę elementów skończonych.

15

Comparison of single and sequential thresholding applied to segmentation of a cell cluster at Ki-67 staining

Markiewicz T.

Przegląd Elektrotechniczny

|

2011

|

R. 87, nr 5

104-106

EN

The paper presents the comparison of different approaches to segmentation of a cell cluster in microscopic images at Ki-67 stained tissues. In automatic quantitative analysis appropriate cell segmentation is the most important task. The main problem is a cell bordering or overlapping, which makes different cell clusters very difficult to separate. Different types of cells based on all nuclei can be recognized. Among them there exists bordering with lighted area between nuclei, the bordering without that area but with significant narrow space between nuclei and in the bad case without even this narrow space. In the first case the optimal selection of threshold value, also in the sequential thresholding manner, can be a successful approach. For nuclei bordering with significant narrow border the appropriate distance transformation and the watershed transform is the most common method to separate these cells. The advantages and disadvantages of different approaches to segmentation will be presented and discussed in the study.

PL

W pracy przedstawione jest porównanie różnych metod segmentacji klastrów komórek w obrazach mikroskopowych przy odczynie Ki-67. Jest to obok klasyfikacji komórek główny problem występujący w automatycznej analizie ilościowej preparatów tkanek. Klastry komórek są obiektami obrazu bardzo trudnymi do właściwej segmentacji i związane są ze stykaniem lub nakładaniem się profili jąder komórek. Można odróżnić kilka rodzajów klastrów: z jaśniejszym obszarem pomiędzy jądrami komórek, bez takiego obszaru ale z przewężeniem powierzchni oraz w najtrudniejszym przypadku bez przejaśnień i przewężeń. W pierwszym z wymienionych przypadków skutecznym podejściem jest odpowiedni wybór progu do progowania, w tym podejście oparte na progowaniu sekwencyjnym. W drugim przypadku dobre efekty daje metoda działów wodnych w połączeniu z właściwą transformacją odległościową. Skuteczność rozważanych w pracy podejść segmentacji klastrów komórek zostanie zaprezentowana i skomentowana.

16

Optimization of thresholding algorithms' parameters for radiographic weld inspection

Napierała L.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2011

|

nr 3

32-35

EN

In this paper, review of selected thresholding algorithms with focus on their use in radiological inspection of welded joints is presented. Described algorithms' parameters are optimized to improve defect visibility. Tests with use of shipbuilding industry radiographic images are carried out and described. Also, comparison of discussed algorithms is presented and their suitability for the use analysed.

PL

W niniejszej pracy zaprezentowano wybrane algorytmy progowania, ze szczególnym uwzględnieniem możliwości ich wykorzystania do analizy cyfrowych radiograficznych zdjęć połączeń spawanych. Parametry opisanych progowań zostały zoptymalizowane pod kątem jak najwierniejszej separacji defektów od tła. Ponadto przedstawiono efekty walidacji uzyskanych parametrów z użyciem dużej bazy zdjęć pochodzących z rutynowych kontroli przeprowadzanych w przemyśle stoczniowym.

17

Determination of bone volume porosity based on histograms of the mCT scans

Gadzała P., Szczepański Z., Zych G.

Challenges of Modern Technology

|

2010

|

Vol. 1, no. 1

88--89

EN

The new method is proposed in the paper for determination of volume porosity of bone tissue based on histograms of 3D mCT scans and also precise defi nition of the threshold value of relative density preserving calculated volume porosity during the reconstruction of the binary image of sample. In this method the normed histogram is considered as a probability distribution of relative mass density in the bone sample. It was shown that the normed histograms of increasing 3D sample are convergent to the limit curve which can be interpreted as a representative histogram of given sample. The limit histograms have been used to determine: the distributions of relative densities in the sets of voxels of pore and skeleton type and their characteristics, the volume porosities of both samples and thresholds values of their binarisation.

18

Application of Micro Computer Tomography to Identification of Pore Structure Parameters of Porous Materials

Szczepański Z., Cieszko M., Gadzała P., Zych G.

Challenges of Modern Technology

|

2010

|

Vol. 1, no. 1

90--91

EN

The purpose of this paper is to apply the scans of microscopic geometry of human bones obtained by Micro Komputer Tomography method to identifi cation of their macroscopic pore structure parameters: volume porosity, permeability and tortuosity of pores and skeleton. These parameters, except the volume porosity, have been determined by simulations of microscopic processes of viscous fl uid fl ow and electrical current passage through virtual models of bones samples. The simulations wave performed using the COMSOL’s Multiphysics environment assigned for solution of boundary value problems described by partial diff erential equations, by use of the fi nite element method.

19

Hand Radiograph Analysis and Joint Space Location Improvement for Image Interpretation

Zieliński B.

Schedae Informaticae

|

2009

|

Vol. 17/18

45-61

EN

Hand radiograph analysis is extremely exhausting and time consuming for radiologists, not because of the complexity, but because of the precision required during diagnosis. Due to this fact, automatic analysis of the joint space width of all joints in a hand would be indispensable. In the following paper, an improvement of a method used to quantify the minimal JSW in hand radiographs, proposed by the author in his previous works, is considered. The proposed changes have an impact on initial pre-processing and joint space location. As a result of experiments conducted on more than 1100 joint spaces, the overall error of pre-processing and joint location decreases from 10.8% to 2.59% after changes.

20

Second Order Fuzzy Measure and Weighted Co-Occurrence Matrix for Segmentation of Brain MR Images

Maji P., Kundu M.K., Chanda B.

Fundamenta Informaticae

|

2008

|

Vol. 88, nr 1-2

161-176

EN

A robust thresholding technique is proposed in this paper for segmentation of brain MR images. It is based on the fuzzy thresholding techniques. Its aim is to threshold the gray level histogram of brain MR images by splitting the image histogram into multiple crisp subsets. The histogram of the given image is thresholded according to the similarity between gray levels. The similarity is assessed through a second order fuzzy measure such as fuzzy correlation, fuzzy entropy, and index of fuzziness. To calculate the second order fuzzy measure, a weighted co-occurrence matrix is presented, which extracts the local information more accurately. Two quantitative indices are introduced to determine the multiple thresholds of the given histogram. The effectiveness of the proposed algorithm, along with a comparisonwith standard thresholding techniques, is demonstrated on a set of brain MR images.