Wyniki wyszukiwania - BazTech

1

Basic mechanisms of Brownian string analysis and manipulation

Bartyzel K.

Journal of Applied Computer Science

|

2018

|

Vol. 26, nr 2

7--22

EN

The paper presents the possibilities of using Brownian Strings as an example of Active Contour Model for linguistic description of objects in an image. Having only a notation composed of a combination of characters RULD we can calculate the statistics of the object, such as its surface area, width and height, centroid, and even image moments. The part is thoroughly discussed. The requirements for a combination of characters RULD to be called a Brownian contour are also presented and analysed carefully.

2

Fast edge detection approach based on global optimization convex model and Split Bregman algorithm

Jing Y., Liu J., Liu Z., Cao H.

Diagnostyka

|

2018

|

Vol. 19, No. 2

23--29

EN

Active contour model is a typical and effective closed edge detection algorithm, which has been widely applied in remote sensing image processing. Since the variety of the image data source, the complexity of the application background and the limitations of edge detection, the robustness and universality of active contour model are greatly reduced in the practical application of edge extraction. This study presented a fast edge detection approach based on global optimization convex model and Split Bregman algorithm. Firstly, the proposed approach defined a generalized convex function variational model which incorporated the RSF model’s principle and Chan’s global optimization idea and could get the global optimal solution. Secondly, a fast numerical minimization scheme based on split Bregman iterative algorithm is employed for overcoming drawbacks of noise and others. Finally, the curve evolves to the target boundaries quickly and accurately. The approach was applied in real special sea ice SAR images and synthetic images with noise, fuzzy boundaries and intensity inhomogeneity, and the experiment results showed that the proposed approach had a better performance than the edge detection methods based on the GMAC model and RSF model. The validity and robustness of the proposed approach were also verified.

3

Automatic seed point selection in ultrasound echography images of breast using texture features

Selvan S., Shenbaga Devi S.

Biocybernetics and Biomedical Engineering

|

2015

|

Vol. 35, no. 3

157--168

EN

Automatic segmentation of breast lesions in 2D ultrasound B-scan images via active contours, require a seed point to be selected inside the breast lesion. The grey levels on an ultrasound image of the breast show intensity information. The fat tissue is hypo echoic relative to the surrounding glandular tissue. The glandular parenchyma tissue usually appears homogeneously echogenic as compared with fat lobules. Simple cysts are anechoic. Malignant solid masses are usually heterogeneous, hypo echoic and tend to look intensely black compared to surrounding isoechoic fat. Benign solid masses tend to appear on ultrasound with intense and uniform hyper echogenicity. Texture features represent changes in grey level intensities. This paper proposes a method that can automatically identify a seed point based on texture features and allow automatic contour initialization for level set segmentation. This seed point plotted on an US B-scan image is mapped on to its corresponding elastogram pair. The proposed approach is applied to 199 ultrasound B-scan images of which 52 are benign solid masses, 84 malignant solid masses and 63 simple and complex cysts. The seed point obtained using this approach is mapped to its corresponding elastogram pair in 62 US B-scan and US elastography image pairs. Quantitative experiment results show that our proposed approach can successfully find proper seed points based on texture values, in ultrasound B-scan images and therefore in elastography images, with an overall accuracy of 86.93%. This approach is effective and makes segmentation of breast lesions computationally easier, more accurate and fast.

4

Automatic segmentation of corneal endothelial cells using active contours

Charłampowicz K., Reska D., Bołdak C.

Advances in Computer Science Research

|

2014

|

Nr 11

47--60

EN

We present a new method for segmenting the corneal endothelial cells from microscopic images. It uses multiple active contours initialized by adaptive thresholding and limited with their growing to not overlap. Thanks to the inherent characteristics of the active contour both outcomes can be achieved: cell quantity and delimitation. The tool implementing this approach is built within the MESA framework - an environment for developing and evaluating segmentation techniques. The accuracy is estimated on the base of real microscopic cell images segmented manually.

PL

W artykule zaprezentowano autorską automatyczną metodę segmentacji komórek śródbłonka rogówki oka z obrazów mikroskopowych. Metoda używa wielu aktywnych konturów zainicjalizowanych wewnątrz komórek za pomocą adaptacyjnego progowania i ograniczonych w swoim rozroście tak, aby nie pokrywać się. Metoda został zaimplementowana w środowisku MESA przeznaczonym do rozwoju i ewaluacji technik segmentacji. Jakość segmentacji została oszacowana na rzeczywistych obrazach mikroskopowych w odniesieniu do ręcznie zaznaczonych konturów komórek.

5

Porównanie wybranych metod wyznaczania obszaru płomienia w wizyjnym systemie diagnostycznym

Sawicki D., Kotyra A.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2013

|

nr 4

14--17

PL

W pracy przedstawiono porównanie wybranych metod wykrywania krawędzi dla obrazów spalania pyłu węglowego. Porównano metodę gradientową Canny’ego z metodą zbiorów poziomicowych oraz metodą opartą o model konturu aktywnego Chan-Vese. Wyniki badań pokazują, że metoda korzystająca z modelu Chan-Vese dobrze odwzorowała brzeg obszaru.

EN

This paper presents comparison edge detection method of combustion pulverized coal. Compared method are: Canny edge detection operator, level set method and Chan-Vese active contour method. Experimental results show that edges extracted with method based on Chan-Vese active contour model gives good result.

6

Wykorzystanie konturu aktywnego do określenia obszaru płomienia w wizyjnym systemie diagnostycznym

Kotyra A., Sawicki D., Gromaszek K., Smolarz A.

Elektronika : konstrukcje, technologie, zastosowania

|

2012

|

Vol. 53, nr 6

27-28

PL

W pracy przedstawiono porównanie wybranych metod wykrywania krawędzi dla obrazów spalania pyłu węglowego. Porównano metodę gradientową Canny'ego z metodą zbiorów poziomicowych oraz metodą opartą o model konturu aktywnego Chan-Vese. Wyniki badań pokazują, że metoda korzystająca z modelu Chan-Vese dobrze odwzorowała brzeg obszaru.

EN

This paper presents comparison edge detection method of combustion pulverized coal. Compared method are: Canny edge detection operator, level set method and Chan-Vese active contour method. Experimental results show that edges extracted with method based on Chan-Vese active contour model gives good result.

7

Elevated active contour with global image energy based on electrostatic force

Bołdak C.

Zeszyty Naukowe Politechniki Białostockiej. Informatyka

|

2010

|

Z. 6

5-21

EN

In this article a new modification of the well known segmentation technique, namely active contour - snake, was proposed. This modification consists in a new formulation of its external force based on the electrostatics. However the base idea of giving electric charges to the image and the snake has been already presented in several works, none of them clearly adressed the problem where the charged snake took place of a charged pixel. In this situation the electrostatic force is not defined, since the distance between charges is zero. The snake proposed in this work evolves on a plane elevated above the image, what never allows this distance to become zero. The method was implemented and verified on real microscopic images of oocytes, proving its superiority on the classic snake.

PL

W artykule tym zaprezentowana jest nowa modyfikacja techniki segmentacji znanej pod nazwą aktywnego konturu - węża. Polega ona na nowym sformułowaniu siły zewnętrznej opartej na sile elektrostatycznej. W istniejących pracach, w których obraz i kontur posiadały ładunek elektryczny, omijano problem konturu zajmującego pozycję naładowanego piksela. W takiej sytuacji siła elektrostatyczna jest niezdefiniowana, gdyż odległość między ładunkami jest zerowa. Proponowany w tej pracy kontur operuje na płaszczyźnie wyniesionej ponad obraz, co sprawia, że odległość ta nigdy nie spada do zera. Metoda została zaimplementowana i zweryfikowana na rzeczywistych obrazach mikroskopowych oocytów, gdzie wykazała swoją wyższość nad klasyczną techniką węża.