Navigation überspringen
Universitätsbibliothek Heidelberg
Status: Bibliographieeintrag

Verfügbarkeit
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Kiechle, Martin [VerfasserIn]   i
 Storath, Martin [VerfasserIn]   i
 Weinmann, Andreas [VerfasserIn]   i
 Kleinsteuber, Martin [VerfasserIn]   i
Titel:Model-based learning of local image features for unsupervised texture segmentation
Verf.angabe:Martin Kiechle, Martin Storath, Andreas Weinmann, and Martin Kleinsteuber
E-Jahr:2018
Jahr:January 26, 2018
Umfang:14 S.
Fussnoten:Gesehen am 21.10.2019
Titel Quelle:Enthalten in: Institute of Electrical and Electronics EngineersIEEE transactions on image processing
Ort Quelle:New York, NY : IEEE, 1992
Jahr Quelle:2018
Band/Heft Quelle:27(2018), 4, Seite 1994-2007
ISSN Quelle:1941-0042
Abstract:Features that capture well the textural patterns of a certain class of images are crucial for the performance of texture segmentation methods. The manual selection of features or designing new ones can be a tedious task. Therefore, it is desirable to automatically adapt the features to a certain image or class of images. Typically, this requires a large set of training images with similar textures and ground truth segmentation. In this paper, we propose a framework to learn features for texture segmentation when no such training data is available. The cost function for our learning process is constructed to match a commonly used segmentation model, the piecewise constant Mumford-Shah model. This means that the features are learned such that they provide an approximately piecewise constant feature image with a small jump set. Based on this idea, we develop a two-stage algorithm which first learns suitable convolutional features and then performs segmentation. We note that the features can be learned from a small set of images, from a single image, or even from image patches. The proposed method achieves a competitive rank in the Prague texture segmentation benchmark, and it is effective for segmenting histological images.
DOI:doi:10.1109/TIP.2018.2792904
URL:Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.

Volltext ; Resolving-System: https://doi.org/10.1109/TIP.2018.2792904
 Volltext: https://ieeexplore.ieee.org/document/8255629
 DOI: https://doi.org/10.1109/TIP.2018.2792904
Datenträger:Online-Ressource
Sprache:eng
Sach-SW:Computational modeling
 Cost function
 Data models
 feature extraction
 feature vector
 geometric optimization
 ground truth segmentation
 histological images
 image patches
 image segmentation
 Image segmentation
 image texture
 learning (artificial intelligence)
 learning process
 local image features
 Mathematical model
 model-based learning
 Mumford-Shah model
 piecewise constant feature image
 piecewise constant Mumford-Shah model
 Prague texture segmentation benchmark
 suitable convolutional features
 textural patterns
 Texture segmentation
 texture segmentation methods
 Training data
 unsupervised learning
 unsupervised texture segmentation
K10plus-PPN:1679247190
Verknüpfungen:→ Zeitschrift

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/68442889   QR-Code
zum Seitenanfang