Multi-label Image Segmentation via Max-sum Solver

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F07%3A03135487" target="_blank" >RIV/68407700:21230/07:03135487 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Multi-label Image Segmentation via Max-sum Solver

Original language description

We formulate single-image multi-label segmentation into regions coherent in texture and color as a MAX-SUM problem for which efficient linear programming based solvers have recently appeared. By handling more than two labels, we go beyond widespread binary segmentation methods, e.g., MIN-CUT or normalized cut based approaches. We show that the MAX-SUM solver is a very powerful tool for obtaining the MAP estimate of a Markov random field (MRF). We build the MRF on superpixels to speed up the segmentationwhile preserving color and texture. We propose new quality functions for setting the MRF, exploiting priors from small representative image seeds, provided either manually or automatically. We show that the proposed automatic segmentation method outperforms previous techniques in terms of the Global Consistency Error evaluated on the Berkeley segmentation database.

Czech name

Multi-label Image Segmentation via Max-sum Solver

Czech description

We formulate single-image multi-label segmentation into regions coherent in texture and color as a MAX-SUM problem for which efficient linear programming based solvers have recently appeared. By handling more than two labels, we go beyond widespread binary segmentation methods, e.g., MIN-CUT or normalized cut based approaches. We show that the MAX-SUM solver is a very powerful tool for obtaining the MAP estimate of a Markov random field (MRF). We build the MRF on superpixels to speed up the segmentationwhile preserving color and texture. We propose new quality functions for setting the MRF, exploiting priors from small representative image seeds, provided either manually or automatically. We show that the proposed automatic segmentation method outperforms previous techniques in terms of the Global Consistency Error evaluated on the Berkeley segmentation database.

Type

D - Article in proceedings

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

—

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2007

Confidentiality

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

Article name in the collection

CVPR 2007: Proceedings of the Computer Vision and Pattern Recognition conference

ISBN

1-4244-1180-7

ISSN

1053-587X

e-ISSN

—

Number of pages

6

Pages from-to

—

Publisher name

IEEE Computer Society

Place of publication

Los Alamitos

Event location

Minneapolis

Event date

Jun 18, 2007

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—