Model-based learning of local image features for unsupervised texture segmentation
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 ima...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
January 26, 2018
|
| In: |
IEEE transactions on image processing
Year: 2018, Jahrgang: 27, Heft: 4, Pages: 1994-2007 |
| ISSN: | 1941-0042 |
| DOI: | 10.1109/TIP.2018.2792904 |
| Online-Zugang: | Resolving-System, Volltext: https://doi.org/10.1109/TIP.2018.2792904 Resolving-System, Volltext: https://ieeexplore.ieee.org/document/8255629 
|
| Verfasserangaben: | Martin Kiechle, Martin Storath, Andreas Weinmann, and Martin Kleinsteuber |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1679247190 | ||
| 003 | DE-627 | ||
| 005 | 20220817004309.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 191021s2018 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TIP.2018.2792904 |2 doi | |
| 035 | |a (DE-627)1679247190 | ||
| 035 | |a (DE-599)KXP1679247190 | ||
| 035 | |a (OCoLC)1341248263 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 27 |2 sdnb | ||
| 100 | 1 | |a Kiechle, Martin |e VerfasserIn |0 (DE-588)1197569758 |0 (DE-627)1679246178 |4 aut | |
| 245 | 1 | 0 | |a Model-based learning of local image features for unsupervised texture segmentation |c Martin Kiechle, Martin Storath, Andreas Weinmann, and Martin Kleinsteuber |
| 264 | 1 | |c January 26, 2018 | |
| 300 | |a 14 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 21.10.2019 | ||
| 520 | |a 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. | ||
| 650 | 4 | |a Computational modeling | |
| 650 | 4 | |a Cost function | |
| 650 | 4 | |a Data models | |
| 650 | 4 | |a feature extraction | |
| 650 | 4 | |a feature vector | |
| 650 | 4 | |a geometric optimization | |
| 650 | 4 | |a ground truth segmentation | |
| 650 | 4 | |a histological images | |
| 650 | 4 | |a image patches | |
| 650 | 4 | |a image segmentation | |
| 650 | 4 | |a Image segmentation | |
| 650 | 4 | |a image texture | |
| 650 | 4 | |a learning (artificial intelligence) | |
| 650 | 4 | |a learning process | |
| 650 | 4 | |a local image features | |
| 650 | 4 | |a Mathematical model | |
| 650 | 4 | |a model-based learning | |
| 650 | 4 | |a Mumford-Shah model | |
| 650 | 4 | |a piecewise constant feature image | |
| 650 | 4 | |a piecewise constant Mumford-Shah model | |
| 650 | 4 | |a Prague texture segmentation benchmark | |
| 650 | 4 | |a suitable convolutional features | |
| 650 | 4 | |a textural patterns | |
| 650 | 4 | |a Texture segmentation | |
| 650 | 4 | |a texture segmentation methods | |
| 650 | 4 | |a Training data | |
| 650 | 4 | |a unsupervised learning | |
| 650 | 4 | |a unsupervised texture segmentation | |
| 700 | 1 | |a Storath, Martin |e VerfasserIn |0 (DE-588)1036903818 |0 (DE-627)751410578 |0 (DE-576)389559830 |4 aut | |
| 700 | 1 | |a Weinmann, Andreas |e VerfasserIn |4 aut | |
| 700 | 1 | |a Kleinsteuber, Martin |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |a Institute of Electrical and Electronics Engineers |t IEEE transactions on image processing |d New York, NY : IEEE, 1992 |g 27(2018), 4, Seite 1994-2007 |h Online-Ressource |w (DE-627)325162050 |w (DE-600)2034319-X |w (DE-576)094086281 |x 1941-0042 |7 nnas |
| 773 | 1 | 8 | |g volume:27 |g year:2018 |g number:4 |g pages:1994-2007 |g extent:14 |a Model-based learning of local image features for unsupervised texture segmentation |
| 856 | 4 | 0 | |u https://doi.org/10.1109/TIP.2018.2792904 |x Resolving-System |3 Volltext |
| 856 | 4 | 0 | |u https://ieeexplore.ieee.org/document/8255629 |x Resolving-System |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20191021 | ||
| 993 | |a Article | ||
| 994 | |a 2018 | ||
| 998 | |g 1036903818 |a Storath, Martin |m 1036903818:Storath, Martin |d 700000 |d 708000 |e 700000PS1036903818 |e 708000PS1036903818 |k 0/700000/ |k 1/700000/708000/ |p 2 | ||
| 999 | |a KXP-PPN1679247190 |e 3525767560 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"relHost":[{"titleAlt":[{"title":"Transactions on image processing"}],"part":{"volume":"27","text":"27(2018), 4, Seite 1994-2007","extent":"14","year":"2018","pages":"1994-2007","issue":"4"},"pubHistory":["1.1992 -"],"corporate":[{"role":"aut","roleDisplay":"VerfasserIn","display":"Institute of Electrical and Electronics Engineers"},{"role":"isb","roleDisplay":"Herausgebendes Organ","display":"IEEE Signal Processing Society"}],"language":["eng"],"recId":"325162050","disp":"Institute of Electrical and Electronics EngineersIEEE transactions on image processing","note":["Gesehen am 10.09.02"],"type":{"media":"Online-Ressource","bibl":"periodical"},"title":[{"title_sort":"IEEE transactions on image processing","title":"IEEE transactions on image processing","subtitle":"a publication of the IEEE Signal Processing Society"}],"physDesc":[{"extent":"Online-Ressource"}],"id":{"issn":["1941-0042"],"eki":["325162050"],"zdb":["2034319-X"]},"origin":[{"publisherPlace":"New York, NY","dateIssuedDisp":"1992-","dateIssuedKey":"1992","publisher":"IEEE"}]}],"physDesc":[{"extent":"14 S."}],"id":{"eki":["1679247190"],"doi":["10.1109/TIP.2018.2792904"]},"origin":[{"dateIssuedKey":"2018","dateIssuedDisp":"January 26, 2018"}],"name":{"displayForm":["Martin Kiechle, Martin Storath, Andreas Weinmann, and Martin Kleinsteuber"]},"language":["eng"],"recId":"1679247190","type":{"bibl":"article-journal","media":"Online-Ressource"},"note":["Gesehen am 21.10.2019"],"title":[{"title":"Model-based learning of local image features for unsupervised texture segmentation","title_sort":"Model-based learning of local image features for unsupervised texture segmentation"}],"person":[{"family":"Kiechle","given":"Martin","roleDisplay":"VerfasserIn","display":"Kiechle, Martin","role":"aut"},{"family":"Storath","given":"Martin","display":"Storath, Martin","roleDisplay":"VerfasserIn","role":"aut"},{"given":"Andreas","family":"Weinmann","role":"aut","display":"Weinmann, Andreas","roleDisplay":"VerfasserIn"},{"display":"Kleinsteuber, Martin","roleDisplay":"VerfasserIn","role":"aut","family":"Kleinsteuber","given":"Martin"}]} | ||
| SRT | |a KIECHLEMARMODELBASED2620 | ||