2010
DOI: 10.1016/j.imavis.2009.04.019
|View full text |Cite
|
Sign up to set email alerts
|

Maximum likelihood estimation of vessel parameters from scale space analysis

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
20
0
3

Year Published

2012
2012
2023
2023

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 53 publications
(23 citation statements)
references
References 22 publications
0
20
0
3
Order By: Relevance
“…This method uses adaptive local thresholding to produce a binary image then extract large connected components as large vessels. The residual fragments in the binary image including some thin vessel segments (or pixels), are classified by Support Vector Machine (SVM [85], Radius based Clustering Algorithm (RACAL) [88] which uses a distance based principle to map the distributions of the image pixels. Among the above discussed approaches, the performance of algorithms based on supervised classification is better in general than their counterparts.…”
Section: Supervised Classificationmentioning
confidence: 99%
“…This method uses adaptive local thresholding to produce a binary image then extract large connected components as large vessels. The residual fragments in the binary image including some thin vessel segments (or pixels), are classified by Support Vector Machine (SVM [85], Radius based Clustering Algorithm (RACAL) [88] which uses a distance based principle to map the distributions of the image pixels. Among the above discussed approaches, the performance of algorithms based on supervised classification is better in general than their counterparts.…”
Section: Supervised Classificationmentioning
confidence: 99%
“…Подходы, основанные на классификации пикселей без использования обуче-ния, осуществляют поиск шаблонов, характерных для кровяных сосудов на изображениях сетчатки. В этих алгоритмах не требуется непосредственного исполь-зования обучающей выборки [67][68][69][70][71][72][73][74][75][76]. В работах [67,68] был предложен метод разрастания областей на ос-нове анализа информации о градиенте и кривизне по-ля.…”
Section: методы сегментации (г)unclassified
“…Тести-рование проводилось на базе DRIVE и показало точ-ность метода в 97,59%. Ng et al [73] разработал сис-тему детектирования сосудов, основанную на вероят-ностной модели. Авторы применяли фильтр с раз-личным масштабом на основе второй производной функции Гаусса к изображению, а отклик фильтра использовался для детектирования сосудов и оценки их признаков.…”
Section: методы сегментации (г)unclassified
“…Penyeragaman tingkat pencahayaan atau perbaikan tingkat pencahayaan yang tidak seragam dapat dilakukan dengan berbagai cara antara lain penggunaan turunan kedua Gaussian Filter pada citra dalam beberapa tingkat, dan keluaran filter ini digunakan untuk menyimpulkan adanya sifat pembuluh darah [12]. Selain itu Median Filter digunakan untuk citra yang mengandung multipercabangan sehingga keluaran dari Median Filter adalah mengurangi atau menghilangkan noise percabangan citra pembuluh darah [13].…”
Section: Penyeragaman Tingkat Pencahayaanunclassified