BazTech - Yadda

1

Iceberg detection and tracking using two-level feature extraction methodology on Antarctica Ocean

Krishnan Rajakumar, Thangavelu Arunkumar, Panneer Prabhavathy, Devulapalli Sudheer, Misra Arundhati, Putrevu Deepak

Acta Geophysica

|

2022

|

Vol. 70, no 6

2953--2963

EN

This paper aims to develop an automatic feature extraction system for detecting icebergs in Antarctica. Extracting suitable features to discriminate an iceberg from sea ice and land melting based on its content is tedious. Especially in Synthetic Aperture Radar data, high image content is highly affected by speckle noise. Establishing the appropriate spatial relationship between pixels is not producing much accuracy with the standard low-level features. The proposed method introduces the two-level iceberg detection and tracking algorithm. The available samples were used to train the first-level convolution neural network-based features. False-positive predictions have been removed using the multiscale contourlet-based Haralick texture features in the second level. The final detected iceberg movement has been tracked using the temporal image data. The distance moved in both temporal images is computed with the help of latitude and longitude information. The proposed methodology exhibited the best performance over state-of-the-art methods and acquired 79.1% precision and 83.8 F1 score.

2

Fast Fourier Transform detection and reduction of high-frequency errors from the results of surface topography profile measurements of honed textures

Podulka Przemysław

Eksploatacja i Niezawodność

|

2021

|

Vol. 23, no. 1

84--93

EN

In this paper, various type of noise detection procedures with surface topography profile analysis were proposed, compared (studied) and suggested. The honed cylinder liner surface textures with additionally burnished oil pockets were measured with a stylus or optical approaches. Measurement errors, defined as high-frequency measurement noise, were taken into sufficient consideration. It was proposed to select the noise detection methods more with profile (2D) than areal (3D) assessments; some-frequency noise was much easier to observe in profile than surface analysis. Moreover, applications of various type of regular filtration methods, mostly based on Gaussian functions, were compared with Fast Fourier Transform filtration for detection or reduction of some (high) frequency-defined measurement errors.

3

An automated computer-aided diagnosis system for classification of MR images using texture features and gbest-guided gravitational search algorithm

Shanker Ravi, Bhattacharya Mahua

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 2

815--835

EN

The segmentation and classification of brain magnetic resonance (MR) images are the crucial and challenging task for radiologists. The conventional methods for analyzing brain images are time-consuming and ineffective in decision-making. Thus, to overcome these limita-tions, this work proposes an automated and robust computer-aided diagnosis (CAD) system for accurate classification of normal and abnormal brain MR images. The proposed CAD system has the ability to assist the radiologists for diagnosis of brain MR images at an early stage of abnormality. Here, to improve the quality of images before their segmentation, contrast limited adaptive histogram equalization (CLAHE) is employed. The segmentation of the region of interest is obtained using the multilevel Otsu's thresholding algorithm. In addition, the proposed system selects the most significant and relevant features from the texture and multiresolution features. The multiresolution features are extracted using discrete wavelet transform (DWT), stationary wavelet transform (SWT), and fast discrete curvelet transform (FDCT). Moreover, the Tamura and local binary pattern (LBP) are used to extract the texture features from the images. These features are used to classify the brain MR images using feedforward neural network (FNN) classifier, where different meta-heuristic optimization algorithms, e.g., genetic algorithm (GA), particle swarm optimization (PSO), gravitational search algorithm (GSA), and gbest-guided gravitational search algorithm (GG-GSA) are employed for optimizing the weights and biases of FNN. The extensive experimen-tal results on DS-195, DS-180, and three standard datasets show that the classification accuracy of GG-GSA based FNN classifier outperforms all mentioned meta-heuristic-based classifiers and several state-of-the-art methods.

4

Effect of despeckle filtering on classification of breast tumors using ultrasound images

Kriti, Virmani Jitendra, Agarwal Ravinder

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 2

536--560

EN

Ultrasound is the most widely used imaging modality for screening of breast tumors. However, due to the presence of speckle noise in an ultrasound image, the diagnostic information gets masked and the interpretation of the breast abnormalities becomes difficult for the radiologist. The texture of the tumor region and the shape/margin characteristics are considered to be important parameters for the analysis of the breast tumors. In the present work, exhaustive experimentation has been carried out for the design of CAD systems for classification of breast tumors by considering (a) original images only, (b) despeckled images only and (c) both original and despeckled images together (hybrid approach). Total 100 breast ultrasound images (40 benign and 60 malignant) have been used for the analysis. Initially, these images have been despeckled using six filters namely Lee sigma, BayesShrink, DPAD, FI, FB and HFB filters. Total 162 features (149 texture and 13 morphological features) have been computed from both original and despeckled breast ultrasound images and SVM classifier has been used extensively for the classification. The results of the study indicate that the hybrid approach of CAD system design using texture features computed from original images combined with morphological features computed from images despeckled by DPAD filter yield optimal performance for classifica-tion of benign and malignant breast tumors with a classification accuracy of 96.0%. From the promising results of the study it can be concluded that the proposed hybrid CAD system design could be used as a second opinion tool in clinical setting.

5

Selected features of carbonate rocks based on the X-ray computed tomography method (CT)

Urbaniec A., Drabik K., Dohnalik M.

Nafta-Gaz

|

2018

|

R. 74, nr 3

183--192

EN

The paper presents possibilities of X-ray computed tomography (CT) application in view of representing selected features of carbonate rocks in a CT image. 72 sections of drill cores, approx. 1 m long each, were selected for tomographic examinations to obtain as reliable as possible results. The selected core material represents carbonate formations of various ages (from Palaeozoic to Upper Cretaceous), originating from boreholes situated in the Carpathian Foreland area. The interpretation of tomographic examinations was connected with a detailed sedimentological analysis of selected core sections, allowing to carry out direct comparisons, which of studied features and to what extent have disclosed in the CT images, and also whether this image can supplement or make the prepared descriptions more detailed. The presented information has a qualitative nature, i.e. referring mainly to descriptive features of the analysed carbonate rocks. Because of a limited size of the paper we have focused only on a few from numerous analysed features of carbonate rocks. The method of X-ray computed tomography (CT) can be very helpful at the analysis of various carbonate rocks features, such as structural and textural features, biogenic structures, porosity, and fracturing. It should be emphasised that this is a non-invasive method, providing a possibility to reproduce the CT image in various directions, without the necessity of mechanical interference in the rock material, resulting in the core destruction. Mummified siliceous sponges were examples of biogenic structures, which were best reflected in formations, which have been subjected to processes of selective dolomitization. In such type of carbonate rocks the sponge mummies were not dolomitized, while the basic material of the background was dolomitized. A very good representation of the structure in CT images was obtained for colonial hexacorals from the Scleractinia group, because many details of their skeleton structure are noticeable. Contrary to siliceous sponges the structure of corals is preserved much worse in the case, when the studied deposits were subject to diagenetic processes (such as dissolution, recrystallisation, or dolomitization). In addition, the analysis of various bioclasts, preserved in carbonate rocks, has shown a significant role both of the original mineral component building the skeletal elements of organisms (aragonite, high-magnesium calcite, lowmagnesium calcite), and of diagenetic processes history, directly affecting the condition of those components preservation. Based on the analysed materials it was found that porosity and fracturing are among best reflected features of carbonate rocks in the CT image. Open fractures, fractures filled with anhydrite and fractures filled with clay-marly material are generally well reflected in the CT image. Instead, fractures filled with calcite are variously recognisable, depending on the mineral composition of the rock background.

PL

W artykule przedstawiono możliwości wykorzystania rentgenowskiej tomografii komputerowej (CT) pod kątem odzwierciedlenia wybranych cech skał węglanowych w obrazie CT. Do badań tomograficznych wytypowano 72 odcinki rdzeni wiertniczych o długości ok. 1 m każdy w celu uzyskania możliwie najbardziej wiarygodnych wyników. Wytypowany materiał rdzeniowy reprezentuje utwory węglanowe różnego wieku (od paleozoiku po górną kredę), pochodzące z otworów wiertniczych, zlokalizowanych na obszarze przedgórza i w podłożu Karpat. Interpretację badań tomograficznych powiązano ze szczegółową analizą sedymentologiczną wybranych odcinków rdzeni, co pozwoliło na bezpośrednie porównanie, które z badanych cech i w jakim stopniu ujawniły się w obrazie tomograficznym, a także czy obraz ten jest w stanie uzupełnić lub uszczegółowić wykonane opisy. Przedstawione informacje mają charakter jakościowy, tj. odnoszący się głównie do cech opisowych analizowanych skał węglanowych. W związku z ograniczoną objętością artykułu skoncentrowano się jedynie na kilku spośród wielu przeanalizowanych cech skał węglanowych. Metoda rentgenowskiej tomografii komputerowej (CT) może być bardzo pomocna przy analizie różnego typu ich cech, takich jak: cechy strukturalne i teksturalne, struktury biogeniczne, porowatość, szczelinowatość. Należy podkreślić, że jest to metoda nieinwazyjna, dająca możliwość odtwarzania obrazu tomograficznego w różnych kierunkach, bez konieczności mechanicznej ingerencji w materiał skalny, prowadzącej do niszczenia rdzenia. Spośród przeanalizowanych struktur biogenicznych uwagę zwrócono na zmumifikowane gąbki krzemionkowe, które w najlepszym stopniu odwzorowane zostały w zapisie CT w utworach, które w trakcie diagenezy poddane zostały procesom selektywnej dolomityzacji. W tego typu utworach mumie gąbek nie uległy dolomityzacji, podczas gdy masa podstawowa otaczającego osadu została zdolomityzowana. Bardzo dobre odzwierciedlenie struktury w zapisie CT uzyskano dla kolonijnych koralowców sześciopromiennych z grupy Scleractinia, gdyż w obrazie tomograficznym dostrzegalnych jest wiele detali budowy ich szkieletu. W przeciwieństwie do gąbek krzemionkowych, struktura koralowców zachowana jest znacznie gorzej w przypadku, gdy badane utwory poddane zostały w większym stopniu procesom diagenetycznym (takim jak rozpuszczanie, rekrystalizacja czy też dolomityzacja). Ponadto analiza różnego typu bioklastów, zachowanych w skałach węglanowych, wykazała istotną rolę, zarówno pierwotnego składnika mineralnego budującego elementy szkieletowe organizmów (aragonit, kalcyt wysokomagnezowy, kalcyt niskomagnezowy), jak również historii procesów diagenetycznych, mających bezpośredni wpływ na stan zachowania tych elementów. Na podstawie przeanalizowanych materiałów stwierdzono, że porowatość i szczelinowatość są jednymi z najlepiej odwzorowanych w zapisie tomograficznym cech skał węglanowych. W obrazie CT na ogół w bardzo dobrym stopniu czytelne są szczeliny otwarte, szczeliny wypełnione anhydrytem oraz szczeliny wypełnione materiałem ilasto-marglistym. Natomiast szczeliny zabliźnione kalcytem rozpoznawalne są w różnym stopniu, w zależności od składu mineralnego tła skalnego.

6

Przetwarzanie zdjęć lotniczych na podstawie tekstury

Kućko M., Gracki K.

Elektronika : konstrukcje, technologie, zastosowania

|

2018

|

Vol. 59, nr 5

18--20

PL

Istotną grupę cech obrazu, na podstawie których dokonuje się segmentacji i klasyfikacji, stanowią cechy tekstury, rozumiane jako zależności między powtarzającymi się wzorcami charakterystycznymi dla danego materiału. W artykule porównane zostaną trzy metody analizy tekstury - energia Gabora, operator grating cells i cechy Haralicka - oraz zaproponowane zostaną sposoby poprawy jakości wyników uzyskanych z ich użyciem. Szczególny nacisk położony będzie na zastosowanie porównywanych metod w przetwarzaniu zdjęć lotniczych. Przedstawione zostanie również alternatywne podejście do rozpoznawania wzorców polegające na klasyfikacji prostokątnych bloków obrazu o stopniowo zmniejszających się rozmiarach.

EN

The important group of image features, based on which segmentation and classification is performed, are textural features, understood as dependencies between recurring patterns characteristic of a given material. In the article three methods of texture analysis – Gabor energy, grating cells operator and Haralick features – will be compared, and techniques for improving quality of their results will be proposed. The particular focus will be placed on the application of compared methods in aerial images processing. The alternative approach of pattern recognition, based on the classification of rectangular blocks of an image with gradually decreasing sizes, will be demonstrated.

7

Improvement in the diagnosis of melanoma and dysplastic lesions by introducing ABCD-PDT features and a hybrid classifier

Zakeri A., Hokmabadi A.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 3

456--466

EN

Melanoma and dysplastic lesions are pigmented skin lesions whose accurate classification is of great importance. In this paper, we have proposed a computer-aided diagnosis (CAD) system to improve the diagnostic ability of the conventional ABCD (asymmetry, border irregularity, color, and diameter) analysis. We introduced features extracted by local analysis of range of intensity variations within the lesion that describe pigment distribution and texture (PDT) features. The statistical distribution of pigmentation at a specified direction and distance was analyzed through grey level co-occurrence matrix (GLCM). Some other quantitative features were also extracted by computing neighborhood grey-tone difference matrix. These were correlated with human perception of texture. A hybrid classifier was designed for classification of melanoma, dysplastic, and benign lesions. Log-linearized Gaussian mixture neural network (LLGMNN), K-nearest neighborhood (KNN), linear discriminant analysis (LDA), and support vector machine (SVM) construct the hybrid classifier. The proposed system was evaluated on a set of 792 dermoscopy images and the diagnostic accuracies of 96.8%, 97.3%, and 98.8% for melanoma, dysplastic, and benign lesions were achieved, respectively. The results indicate that PDT features are promising features which in combination with the conventional ABCD features are capable of enhancing the classification performance of the pigmented skin lesions.

8

Automated quantification of ultrasonic fatty liver texture based on curvelet transform and SVD

Bharath R., Mishra P. K., Rajalakshmi P.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 1

145--157

EN

Fatty liver is a prevalent disease and is the major cause for the dysfunction of the liver. If fatty liver is untreated, it may progress into chronic diseases like cirrhosis, hepatocellular carcinoma, liver cancer, etc. Early and accurate detection of fatty liver is crucial to prevent the fatty liver progressing into chronic diseases. Based on the severity of fat, the liver is categorized into four classes, namely Normal, Grade I, Grade II and Grade III respectively. Ultrasound scanning is the widely used imaging modality for diagnosing the fatty liver. The ultrasonic texture of liver parenchyma is specific to the severity of fat present in the liver and hence we formulated the quantification of fatty liver as a texture discrimination problem. In this paper, we propose a novel algorithm to discriminate the texture of fatty liver based on curvelet transform and SVD. Initially, the texture image is decomposed into sub-band images with curvelet transform enhancing gradients and curves in the texture, then an absolute mean of the singular values are extracted from each curvelet decomposed image, and used it as a feature representation for the texture. Finally, a cubic SVM classifier is used to classify the texture based on the extracted features. Tested on a database of 1000 image textures with 250 image textures belonging to each class, the proposed algorithm gave an accuracy of 96.9% in classifying the four grades of fat in the liver.

9

Computer assisted classification framework for prediction of acute lymphoblastic and acute myeloblastic leukemia

Rawat J., Singh A., Bhadauria H. S., Virmani J., Devgun J. S.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 4

637--654

EN

Hematological malignancies i.e. acute lymphoid leukemia and acute myeloid leukemia are the types of blood cancer that can affect blood, bone marrow, lymphatic system and are the major contributors to cancer deaths. In present work, an attempt has been made to design a CAC (computer aided classification system) for diagnosis of myeloid and lymphoid cells and their FAB (French, American, and British) characterization. The proposed technique improves the AML and ALL diagnostic accuracy by analyzing color, morphological and textural features from the blood image using image processing and to assist in the development of a computer-aided screening of AML and ALL. This paper endeavors at proposing a quantitative microscopic approach toward the discrimination of malignant from normal in stained blood smear. The proposed technique firstly segments the nucleus from the leukocyte cell background and then computes features for each segmented nucleus. A total of 331 geometrical, chromatic and texture features are computed. A genetic algorithm using support vector machine (SVM) classifier is used to optimize the feature space. Based on optimized feature space, an SVM classifier with various kernel functions is used to eradicate noisy objects like overlapped cells, stain fragments, and other kinds of background noises. The significance of the proposed method is tested using 331 features on 420 microscopic blood images acquired from the online repository provided by the American society of hematology. The results confirmed the viability or potential of using a computer aided classification method to reinstate the monotonous and the reader-dependent diagnostic methods.

10

GLCM and GLRLM based texture features for computer-aided breast cancer diagnosis

Filipczuk P., Fevens T., Krzyżak A., Obuchowicz A.

Journal of Medical Informatics & Technologies

|

2012

|

Vol. 19

109--115

EN

This paper presents 15 texture features based on GLCM (Gray-Level Co-occurrence Matrix) and GLRLM (Gray-Level Run-Length Matrix) to be used in an automatic computer system for breast cancer diagnosis. The task of the system is to distinguish benign from malignant tumors based on analysis of fine needle biopsy microscopic images. The features were tested whether they provide important diagnostic information. For this purpose the authors used a set of 550 real case medical images obtained from 50 patients of the Regional Hospital in Zielona Góra. The nuclei were isolated from other objects in the images using a hybrid segmentation method based on adaptive thresholding and kmeans clustering. Described texture features were then extracted and used in the classification procedure. Classification was performed using KNN classifier. Obtained results reaching 90% show that presented features are important and may significantly improve computer-aided breast cancer detection based on FNB images.

11

Quick texture generation for multiobject image analysis in brain pathology

Warowny M., Markiewicz T.

Przegląd Elektrotechniczny

|

2010

|

R. 86, nr 1

50-52

EN

The paper presents two methods of texture features generation for recognition between neoplasm and non-neoplasm cells in cancer diagnosis. There are few problems which need to be solved to achieve the best results: differentiable images, extraction of the individual cell image, selection of the most important features. We propose two models solving all of these problems. We compare the consequences of implementation Unser’s selected texture features and Markov Random Field model. The results of numerical experiments have shown in both methods quite good accuracy in recognizing cells. The proposed methods have proved to be useful in practical application at the diagnosis of cancer.

PL

Referat przedstawia zastosowanie generacji cech teksturalnych w rozpoznawaniu komórek nowotworowych. Proces rozróżniania komórek jest dość złożony ze względu naturalną złożoność obrazów, konieczność ekstrakcji pojedynczej komórki obrazu oraz trudności w wyborze odpowiednio różnicującej cechy. W pracy porównane zostały efekty zastosowania dwóch rodzajów modeli – opartego na cechach Unsera oraz modelu Markova. Główny nacisk pracy położony jest na praktyczne zastosowanie obu metod w diagnozie nowotworowej.