Sökning: onr:"swepub:oai:DiVA.org:uu-412291" >
Generalised deep le...
Generalised deep learning framework for HEp-2 cell recognition using local binary pattern maps
-
- Bajic, Buda (författare)
- Univ Novi Sad, Fac Tech Sci, Novi Sad, Serbia.
-
- Majtner, Tomas (författare)
- Univ Southern Denmark, Maersk McKinney Moller Inst, Odense, Denmark.
-
- Lindblad, Joakim (författare)
- Uppsala universitet,Bildanalys och människa-datorinteraktion,Avdelningen för visuell information och interaktion,Uppsala Univ, Dept Informat Technol, Ctr Image Anal, Uppsala, Sweden.
-
visa fler...
-
- Sladoje, Natasa (författare)
- Uppsala universitet,Avdelningen för visuell information och interaktion,Bildanalys och människa-datorinteraktion,Uppsala Univ, Dept Informat Technol, Ctr Image Anal, Uppsala, Sweden.
-
visa färre...
-
Univ Novi Sad, Fac Tech Sci, Novi Sad, Serbia Univ Southern Denmark, Maersk McKinney Moller Inst, Odense, Denmark. (creator_code:org_t)
- 2020-04-11
- 2020
- Engelska.
-
Ingår i: IET Image Processing. - : INST ENGINEERING TECHNOLOGY-IET. - 1751-9659 .- 1751-9667. ; 14:6, s. 1201-1208
- Relaterad länk:
-
https://ietresearch....
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- The authors propose a novel HEp-2 cell image classifier to improve the automation process of patients' serum evaluation. The authors' solution builds on the recent progress in deep learning based image classification. They propose an ensemble approach using multiple state-of-the-art architectures. They incorporate additional texture information extracted by an improved version of local binary patterns maps, $\alpha $alpha LBP-maps, which enables to create a very effective cell image classifier. This innovative combination is trained on three publicly available datasets and its general applicability is demonstrated through the evaluation on three independent test sets. The presented results show that their approach leads to a general improvement of performance on average on the three public datasets.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- medical image processing
- learning (artificial intelligence)
- image texture
- image classification
- biological techniques
- deep learning based image classification
- ensemble approach
- texture information
- local binary patterns maps
- effective cell image classifier
- generalised deep learning framework
- HEp-2 cell recognition
- HEp-2 cell image classifier
- local binary pattern mapping
- serum evaluation
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas