Wyniki wyszukiwania - BazTech

1

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.

2

Neural network segmentation of images from stained cucurbits leaves with colour symptoms of biotic and abiotic stresses

Gocławski J., Sekulska-Nalewajko J., Kuźniak E.

International Journal of Applied Mathematics and Computer Science

|

2012

|

Vol. 22, no. 3

669-684

EN

The increased production of Reactive Oxygen Species (ROS) in plant leaf tissues is a hallmark of a plant's reaction to various environmental stresses. This paper describes an automatic segmentation method for scanned images of cucurbits leaves stained to visualise ROS accumulation sites featured by specific colour hues and intensities. The leaves placed separately in the scanner view field on a colour background are extracted by thresholding in the RGB colour space, then cleaned from petioles to obtain a leaf blade mask. The second stage of the method consists in the classification of within mask pixels in a hue-saturation plane using two classes, determined by leaf regions with and without colour products of the ROS reaction. At this stage a two-layer, hybrid artificial neural network is applied with the first layer as a self-organising Kohonen type network and a linear perceptron output layer (counter propagation network type). The WTA-based, fast competitive learning of the first layer was improved to increase clustering reliability. Widrow-Hoff supervised training used at the output layer utilises manually labelled patterns prepared from training images. The generalisation ability of the network model has been verified by K-fold cross-validation. The method significantly accelerates the measurement of leaf regions containing the ROS reaction colour products and improves measurement accuracy.

3

Wpływ wyboru elementu strukturalnego użytego w przetwarzaniu morfologicznym na skuteczność nowej metody usuwania tła z sekwencji MRI

Kalicka R., Lipiński S., Pietrenko-Dąbrowska A.

Zeszyty Naukowe Wydziału ETI Politechniki Gdańskiej. Technologie Informacyjne

|

2008

|

T. 15

165-170

PL

W artykule zaprezentowano nową metodę usuwania zaszumionego tła z sekwencji skanów MRI. Na każdy skan składają się dwa obszary: przekrój mózgu i tło, oba zawierające szum. Tło powinno być odseparowane i wykluczone z dalszej analizy. Cel ten został osiągnięty dzięki zastosowaniu opisanego algorytmu, aplikującego podstawowe operacje morfologiczne: dylację, erozję, otwarcie i zamknięcie do uprzednio zbinaryzowanych obrazów MRI. Pokazano rezultaty przetwarzania z użyciem różnych kształtów i rozmiarów elementów strukturalnych użytych w operacjach morfologicznych. Celem było takie dobranie parametrów tych elementów by opisaną metodę uczynić możliwie uniwersalną i odporną na różnice w wyglądzie i jakości przetwarzanych sekwencji MRI.

EN

The paper presents a new method of removing the noisy background from the sequence of magnetic resonance imaging (MRI) scans. The scans contain the noisy head-cross data and also the noisy background data. The latter have to be removed and excluded from a further analysis. It is achieved by applying same basic morphological operations of dilation, erosion, opening and closing to the previously binarized MRI scans. The results of removing the background from the sequence of scans with the use of same different shapes and sizes of structuring elements are presented in the paper. The aim of this paper is to choose the best structuring elements to make the new method the most immune to various qualities and appearances of the processed MRI images.

4

Application of morphological analysis for gear fault detection and trending

Gryllias K., Yiakopoulos C., Antoniadis I.

Diagnostyka

|

2008

|

nr 4(48)

37-42

EN

Frequency domain based signal processing methods such as cepstrum analysis, Hilbert Transform based demodulation, cyclostationary analysis, etc have been shown to present a quite effective behaviour in the detection of defects, when applied to the analysis of vibration signals, resulting from gear pairs with one or more defective gears. However, these methods typically require some complex and sophisticated analysis, which renders their application cumbersome for applications requiring unskilled personnel or automated fault detection and trending. Alternatively to these methods, morphological analysis for processing vibration signals has been proposed, addressing the issues of how to quantify the shape and the size of the signals directly in the time domain. Morphological analysis and the resulting morphological index is applied in this paper to a set of twelve successive vibration measurements resulting from a gearbox prior to tooth breakage. As shown, the morphological index is able monitor the evolution of the potential fault, providing a clear warning prior to the breakage of the tooth.