Wyniki wyszukiwania - BazTech

1

Robust intensity variation and inverse surface adaptive thresholding techniques for detection of optic disc and exudates in retinal fundus images

Karkuzhali S., Manimegalai D.

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 3

753--764

EN

Diabetic Retinopathy (DR) is an adverse change in retinal blood vessels leads to blindness for diabetic patients without any symptoms. Diabetes is characterized by imbalance level of glucose in the human body. The optic disc (OD) is the major retinal landmark. Localization of OD is an important step in fundus image analysis and to develop Computer Aided Diagnosis tool for DR. OD center detection is necessary to reduce false positive rate in the detection of exudates (EXs). EXs is the white lesion present in the retina which is the early symptom for the diagnosis of DR. OD is detected using intensity variation algorithm and EXs is segmented using inverse surface adaptive thresholding algorithm. This algorithm achieves better result in localizing OD and segmenting EXs when compared to literature-reviewed methods. The maximum intensity variance method is used to locate OD with average ACC of 96.54%, 98.65%, 98.12%, 99.23%, 99.81% and 98.47% in DIARETDB0, DIARETDB1, MESSIDOR, DRIVE, STARE and Bejan Singh Eye Hospital databases with less computation time of 102 ms, 108 ms, 120 ms, 93 ms, 110 ms and 131 ms. The inverse surface adaptive thresholding method has achieved an SE of 97.43%, 98.87%, 99.12%, 97.21%, 98.72%, and 96.63%, a SPE of 91.56%, 92.31%, 90.21%, 90.14%, 89.58%, 92.56% and an ACC of 99.34%, 99.67%, 98.34%, 98.87%, 99.13%, 98.34% for DIARETDB0, DIARETDB1, MESSIDOR, DRIVE, STARE and Bejan Singh Eye Hospital databases respectively.

2

Binarization of document images using the modified local-global Otsu and Kapur algorithms

Lech P., Okarma K., Wojnar D

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 2

71-74

EN

In the paper an algorithm for binarization of grayscale images representing text documents together with its optimization is presented. In the proposed approach two classical global thresholding algorithms proposed by Otsu and Kapur are combined with their local versions applied for blocks. The experimental results have been obtained for the H-DIBCO test dataset containing handwritten text images together with their "groundtruth" binary equivalents.

PL

W artykule zaprezentowano algorytm binaryzacji obrazów w skali szarości przedstawiających dokumenty tekstowe wraz z jego optymalizacją. Przedstawione podejście bazuje na połączeniu dwóch klasycznych metod progowania zaproponowanych przez Otsu i Kapura z ich lokalnymi wariantami zastosowanymi dla bloków. Wyniki eksperymentalne uzyskano dla bazy testowej H-DIBCO zawierającej obrazy rękopisów wraz z ich binarnymi odpowiednikami stanowiącymi wzorce.

3

Segmentation with image thresholding algorithms

Sikorska S.

Challenges of Modern Technology

|

2011

|

Vol. 2, no. 2

19--22

EN

The first step in image analysis and pattern recognition is image segmentation and it is one of the most difficult tasks in image processing. It determines the quality of the final result of analysis because it is very important and critical component. There are hundreds of segmentation techniques in literature. There is no single method which can be considered good for all sorts of images and conditions. In many applications of image processing, the gray levels of pixels belonging to the object are substantially different from the gray levels of the pixels belonging to the background. Thresholding then becomes a simple but effective tool to separate objects from the background. To improve the segmentation results, a strategy consists in combining algorithms in order to obtain a robust segmentation by exploiting the advantages of one method to reduce the drawbacks of the second one. This paper provides a summary of approaches to image segmentation by thresholding available at the present and describes the properties of different kinds of methods and problems encountered. There will be also presented some advanced algorithms with their practical application.

4

Algorytmy programowania sygnałów radiolokacyjnych

Blok E.

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

1998

|

nr 11

810-814

PL

Omówiono zagadnienia progowania sygnałów radiolokacyjnych. Przedstawiono kilka podstawowych algorytmów progowania podając ich wady i zalety.

EN

In this paper the problems of the radar signal thresholding algorithms have been presented. Few main algorithms have been described. There have been given their advantages and faults.