Graduate School and Research Center in Digital Sciences

Towards fully automatic image segmentation evaluation

Goldmann, Lutz; Adamek, Tomasz; Vajda, Peter; Karaman, Mustafa; Mörzinger, Roland; Galmar, Eric; Sikora, Thomas; O'Connor, Noel E; Ha-Minh, Thien; Ebrahimi, Touradj; Schallauer, Peter; Huet, Benoit

ACIVS 2008, Advanced Concepts for Intelligent Vision Systems, October 20-24, 2008, Juan-les-Pins, France / Also published as LNCS, Volume 5259/2008, ISBN: 978-3-540-88457-6

Spatial region (image) segmentation is a fundamental step for many computer vision applications. Although many methods have been proposed, less work has been done in developing suitable evaluation methodologies for comparing different approaches. The main problem of general purpose segmentation evaluation is the dilemma between objectivity and generality. Recently, figure ground segmentation evaluation has been proposed to solve this problem by defining an unambiguous ground truth using the most salient foreground object. Although the annotation of a single foreground object is less complex than the annotation of all regions within an image, it is still quite time consuming, especially for videos. A novel framework incorporating background subtraction for automatic ground truth generation and different foreground evaluation measures is proposed, that allows to effectively and efficiently evaluate the performance of image segmentation approaches. The experiments show that the objective measures are comparable to the subjective assessment and that there is only a slight difference between manually annotated and automatically generated ground truth.

Doi Bibtex

Title:Towards fully automatic image segmentation evaluation
Type:Conference
Language:English
City:Juan-les-Pins
Country:FRANCE
Date:
Department:Data Science
Eurecom ref:2597
Copyright: © Springer. Personal use of this material is permitted. The definitive version of this paper was published in ACIVS 2008, Advanced Concepts for Intelligent Vision Systems, October 20-24, 2008, Juan-les-Pins, France / Also published as LNCS, Volume 5259/2008, ISBN: 978-3-540-88457-6 and is available at : http://dx.doi.org/10.1007/978-3-540-88458-3_51
Bibtex: @inproceedings{EURECOM+2597, doi = {http://dx.doi.org/10.1007/978-3-540-88458-3_51}, year = {2008}, title = {{T}owards fully automatic image segmentation evaluation}, author = {{G}oldmann, {L}utz and {A}damek, {T}omasz and {V}ajda, {P}eter and {K}araman, {M}ustafa and {M}{\"o}rzinger, {R}oland and {G}almar, {E}ric and {S}ikora, {T}homas and {O}'{C}onnor, {N}oel {E} and {H}a-{M}inh, {T}hien and {E}brahimi, {T}ouradj and {S}challauer, {P}eter and {H}uet, {B}enoit}, booktitle = {{ACIVS} 2008, {A}dvanced {C}oncepts for {I}ntelligent {V}ision {S}ystems, {O}ctober 20-24, 2008, {J}uan-les-{P}ins, {F}rance / {A}lso published as {LNCS}, {V}olume 5259/2008, {ISBN}: 978-3-540-88457-6}, address = {{J}uan-les-{P}ins, {FRANCE}}, month = {10}, url = {http://www.eurecom.fr/publication/2597} }
See also: