Supervised and unsupervised segmentation using superpixels, model estimation, and graph cut

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00023001%3A_____%2F17%3A00076325" target="_blank" >RIV/00023001:_____/17:00076325 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/17:00314379 RIV/60461373:22340/17:43913234

Výsledek na webu

<a href="https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging/volume-26/issue-6/061610/Supervised-and-unsupervised-segmentation-using-superpixels-model-estimation-and-graph/10.1117/1.JEI.26.6.061610.short" target="_blank" >https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging/volume-26/issue-6/061610/Supervised-and-unsupervised-segmentation-using-superpixels-model-estimation-and-graph/10.1117/1.JEI.26.6.061610.short</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1117/1.JEI.26.6.061610" target="_blank" >10.1117/1.JEI.26.6.061610</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Supervised and unsupervised segmentation using superpixels, model estimation, and graph cut

Popis výsledku v původním jazyce

Image segmentation is widely used as an initial phase of many image analysis tasks. It is often advantageous to first group pixels into compact, edge-respecting superpixels, because these reduce the size of the segmentation problem and thus the segmentation time by an order of magnitudes. In addition, features calculated from superpixel regions are more robust than features calculated from fixed pixel neighborhoods. We present a fast and general multiclass image segmentation method consisting of the following steps: (i) computation of superpixels; (ii) extraction of superpixel-based descriptors; (iii) calculating image-based class probabilities in a supervised or unsupervised manner; and (iv) regularized superpixel classification using graph cut. We apply this segmentation pipeline to five real-world medical imaging applications and compare the results with three baseline methods: pixelwise graph cut segmentation, supertexton-based segmentation, and classical superpixel-based segmentation. On all datasets, we outperform the baseline results. We also show that unsupervised segmentation is surprisingly efficient in many situations. Unsupervised segmentation provides similar results to the supervised method but does not require manually annotated training data, which is often expensive to obtain.

Název v anglickém jazyce

Supervised and unsupervised segmentation using superpixels, model estimation, and graph cut

Popis výsledku anglicky

Image segmentation is widely used as an initial phase of many image analysis tasks. It is often advantageous to first group pixels into compact, edge-respecting superpixels, because these reduce the size of the segmentation problem and thus the segmentation time by an order of magnitudes. In addition, features calculated from superpixel regions are more robust than features calculated from fixed pixel neighborhoods. We present a fast and general multiclass image segmentation method consisting of the following steps: (i) computation of superpixels; (ii) extraction of superpixel-based descriptors; (iii) calculating image-based class probabilities in a supervised or unsupervised manner; and (iv) regularized superpixel classification using graph cut. We apply this segmentation pipeline to five real-world medical imaging applications and compare the results with three baseline methods: pixelwise graph cut segmentation, supertexton-based segmentation, and classical superpixel-based segmentation. On all datasets, we outperform the baseline results. We also show that unsupervised segmentation is surprisingly efficient in many situations. Unsupervised segmentation provides similar results to the supervised method but does not require manually annotated training data, which is often expensive to obtain.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

30202 - Endocrinology and metabolism (including diabetes, hormones)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of electronic imaging

ISSN

1017-9909

e-ISSN

—

Svazek periodika

26

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

17

Strana od-do

"art. no. 061610"

Kód UT WoS článku

000419961800012

EID výsledku v databázi Scopus

—