Çok Etiketli Imgelerin Geriçatimi için Iyileştirilmiş TvMin+DART Algoritmasi

Ezgi Demircan-Türeyen; Mustafa E. Kamaşak

doi:10.1109/TIPTEKNO.2015.7374561

Çok Etiketli Imgelerin Geriçatimi için Iyileştirilmiş TvMin+DART Algoritmasi

Ezgi Demircan-Türeyen
, Mustafa E. Kamaşak

Bilgisayar Mühendisliği Bölümü

Istanbul Kultur University

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

Özet

From the algebraic point of view, image reconstruction is an under-determined problem, due to the fact that the projection measurements are a lot fewer than the unknown pixels. Discrete algebraic reconstruction technique (DART) is an algorithm used to cope with this situation. DART solves a discrete linear inverse problem by combining an algebraic reconstruction procedure with a threshold segmentation. In order to improve accuracy, the TvMin+DART algorithm modified the subroutines of DART by exploiting total variation minimization technique (TvMin). However, this algorithm was developed for only binary images. In this paper, our TvMin+DART algorithm will be generalized to handle multilabel images as well, and an experimental research to compare the proposed method with the original DART and the conventional filtered backprojection (FBP) will be presented.

Tercüme edilen katkı başlığı	An improved TvMin+DART algorithm to reconstruct multilabel images
Orijinal dil	Türkçe
Ana bilgisayar yayını başlığı	2015 Medical Technologies National Conference, TIPTEKNO 2015
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
ISBN (Elektronik)	9781467377652
DOI'lar	https://doi.org/10.1109/TIPTEKNO.2015.7374561
Yayın durumu	Yayınlandı - 6 Oca 2016
Etkinlik	Medical Technologies National Conference, TIPTEKNO 2015 - Bodrum, Turkey Süre: 15 Eki 2015 → 18 Eki 2015

Yayın serisi

Adı	2015 Medical Technologies National Conference, TIPTEKNO 2015

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	Medical Technologies National Conference, TIPTEKNO 2015
Ülke/Bölge	Turkey
Şehir	Bodrum
Periyot	15/10/15 → 18/10/15

Bibliyografik not

Publisher Copyright:
© 2015 IEEE.

Keywords

algebraic reconstruction techniques
compressed sensing
discrete tomography
threshold segmentation
total variation minimization

Belgeye Erişim

10.1109/TIPTEKNO.2015.7374561

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Demircan-Türeyen, E., & Kamaşak, M. E. (2016). Çok Etiketli Imgelerin Geriçatimi için Iyileştirilmiş TvMin+DART Algoritmasi. In 2015 Medical Technologies National Conference, TIPTEKNO 2015 Makale 7374561 (2015 Medical Technologies National Conference, TIPTEKNO 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TIPTEKNO.2015.7374561

@inproceedings{0e183c113dfc4e7c9f92fcaacffa79b4,

title = "{\c C}ok Etiketli Imgelerin Geri{\c c}atimi i{\c c}in Iyile{\c s}tirilmi{\c s} TvMin+DART Algoritmasi",

abstract = "From the algebraic point of view, image reconstruction is an under-determined problem, due to the fact that the projection measurements are a lot fewer than the unknown pixels. Discrete algebraic reconstruction technique (DART) is an algorithm used to cope with this situation. DART solves a discrete linear inverse problem by combining an algebraic reconstruction procedure with a threshold segmentation. In order to improve accuracy, the TvMin+DART algorithm modified the subroutines of DART by exploiting total variation minimization technique (TvMin). However, this algorithm was developed for only binary images. In this paper, our TvMin+DART algorithm will be generalized to handle multilabel images as well, and an experimental research to compare the proposed method with the original DART and the conventional filtered backprojection (FBP) will be presented.",

keywords = "algebraic reconstruction techniques, compressed sensing, discrete tomography, threshold segmentation, total variation minimization",

author = "Ezgi Demircan-T{\"u}reyen and Kama{\c s}ak, \{Mustafa E.\}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; Medical Technologies National Conference, TIPTEKNO 2015 ; Conference date: 15-10-2015 Through 18-10-2015",

year = "2016",

month = jan,

day = "6",

doi = "10.1109/TIPTEKNO.2015.7374561",

language = "T{\"u}rk{\c c}e",

series = "2015 Medical Technologies National Conference, TIPTEKNO 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2015 Medical Technologies National Conference, TIPTEKNO 2015",

address = "United States",

}

Demircan-Türeyen, E & Kamaşak, ME 2016, Çok Etiketli Imgelerin Geriçatimi için Iyileştirilmiş TvMin+DART Algoritmasi. in 2015 Medical Technologies National Conference, TIPTEKNO 2015., 7374561, 2015 Medical Technologies National Conference, TIPTEKNO 2015, Institute of Electrical and Electronics Engineers Inc., Medical Technologies National Conference, TIPTEKNO 2015, Bodrum, Turkey, 15/10/15. https://doi.org/10.1109/TIPTEKNO.2015.7374561

Çok Etiketli Imgelerin Geriçatimi için Iyileştirilmiş TvMin+DART Algoritmasi. / Demircan-Türeyen, Ezgi; Kamaşak, Mustafa E.
2015 Medical Technologies National Conference, TIPTEKNO 2015. Institute of Electrical and Electronics Engineers Inc., 2016. 7374561 (2015 Medical Technologies National Conference, TIPTEKNO 2015).

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

TY - GEN

T1 - Çok Etiketli Imgelerin Geriçatimi için Iyileştirilmiş TvMin+DART Algoritmasi

AU - Demircan-Türeyen, Ezgi

AU - Kamaşak, Mustafa E.

PY - 2016/1/6

Y1 - 2016/1/6

N2 - From the algebraic point of view, image reconstruction is an under-determined problem, due to the fact that the projection measurements are a lot fewer than the unknown pixels. Discrete algebraic reconstruction technique (DART) is an algorithm used to cope with this situation. DART solves a discrete linear inverse problem by combining an algebraic reconstruction procedure with a threshold segmentation. In order to improve accuracy, the TvMin+DART algorithm modified the subroutines of DART by exploiting total variation minimization technique (TvMin). However, this algorithm was developed for only binary images. In this paper, our TvMin+DART algorithm will be generalized to handle multilabel images as well, and an experimental research to compare the proposed method with the original DART and the conventional filtered backprojection (FBP) will be presented.

AB - From the algebraic point of view, image reconstruction is an under-determined problem, due to the fact that the projection measurements are a lot fewer than the unknown pixels. Discrete algebraic reconstruction technique (DART) is an algorithm used to cope with this situation. DART solves a discrete linear inverse problem by combining an algebraic reconstruction procedure with a threshold segmentation. In order to improve accuracy, the TvMin+DART algorithm modified the subroutines of DART by exploiting total variation minimization technique (TvMin). However, this algorithm was developed for only binary images. In this paper, our TvMin+DART algorithm will be generalized to handle multilabel images as well, and an experimental research to compare the proposed method with the original DART and the conventional filtered backprojection (FBP) will be presented.

KW - algebraic reconstruction techniques

KW - compressed sensing

KW - discrete tomography

KW - threshold segmentation

KW - total variation minimization

UR - https://www.scopus.com/pages/publications/84964294856

U2 - 10.1109/TIPTEKNO.2015.7374561

DO - 10.1109/TIPTEKNO.2015.7374561

M3 - Konferans katkısı

AN - SCOPUS:84964294856

T3 - 2015 Medical Technologies National Conference, TIPTEKNO 2015

BT - 2015 Medical Technologies National Conference, TIPTEKNO 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - Medical Technologies National Conference, TIPTEKNO 2015

Y2 - 15 October 2015 through 18 October 2015

ER -

Çok Etiketli Imgelerin Geriçatimi için Iyileştirilmiş TvMin+DART Algoritmasi

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

Keywords

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap