Eliciting perceptual ground truth for image segmentation

Victoria Hodge; Garry Hollier; John Eakins; Jim Austin

doi:10.1007/11788034_33

Eliciting perceptual ground truth for image segmentation

Victoria Hodge, Garry Hollier, John Eakins, Jim Austin

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we investigate human visual perception and establish a body of ground truth data elicited from human visual studies. We aim to build on the formative work of Ren, Eakins and Briggs who produced an initial ground truth database. Human participants were asked to draw and rank their perceptions of the,parts of a series of figurative images. These rankings were then used to score the perceptions, identify the preferred human breakdowns and thus allow us to induce perceptual rules for human decomposition of figurative images. The results suggest that the human breakdowns follow well-known perceptual principles in particular the Gestalt laws.

Original language	English
Title of host publication	IMAGE AND VIDEO RETRIEVAL, PROCEEDINGS
Editors	H Sundaram, M Naphade, JR Smith, Y Rui
Place of Publication	BERLIN
Publisher	Springer
Pages	320-329
Number of pages	10
ISBN (Print)	3-540-36018-2
DOIs	https://doi.org/10.1007/11788034_33
Publication status	Published - 2006
Event	5th International Conference on Image and Video Retrieval (CIVR 2006 - Tempe Duration: 13 Jul 2006 → 15 Jul 2006

Conference

Conference	5th International Conference on Image and Video Retrieval (CIVR 2006
City	Tempe
Period	13/07/06 → 15/07/06

Keywords

PARTS

Access to Document

10.1007/11788034_33

Cite this

@inproceedings{58c64cb83d824019b4d97c89116f941c,

title = "Eliciting perceptual ground truth for image segmentation",

abstract = "In this paper, we investigate human visual perception and establish a body of ground truth data elicited from human visual studies. We aim to build on the formative work of Ren, Eakins and Briggs who produced an initial ground truth database. Human participants were asked to draw and rank their perceptions of the,parts of a series of figurative images. These rankings were then used to score the perceptions, identify the preferred human breakdowns and thus allow us to induce perceptual rules for human decomposition of figurative images. The results suggest that the human breakdowns follow well-known perceptual principles in particular the Gestalt laws.",

keywords = "PARTS",

author = "Victoria Hodge and Garry Hollier and John Eakins and Jim Austin",

year = "2006",

doi = "10.1007/11788034_33",

language = "English",

isbn = "3-540-36018-2",

pages = "320--329",

editor = "H Sundaram and M Naphade and JR Smith and Y Rui",

booktitle = "IMAGE AND VIDEO RETRIEVAL, PROCEEDINGS",

publisher = "Springer",

address = "Germany",

note = "5th International Conference on Image and Video Retrieval (CIVR 2006 ; Conference date: 13-07-2006 Through 15-07-2006",

}

TY - GEN

T1 - Eliciting perceptual ground truth for image segmentation

AU - Hodge, Victoria

AU - Hollier, Garry

AU - Eakins, John

AU - Austin, Jim

PY - 2006

Y1 - 2006

N2 - In this paper, we investigate human visual perception and establish a body of ground truth data elicited from human visual studies. We aim to build on the formative work of Ren, Eakins and Briggs who produced an initial ground truth database. Human participants were asked to draw and rank their perceptions of the,parts of a series of figurative images. These rankings were then used to score the perceptions, identify the preferred human breakdowns and thus allow us to induce perceptual rules for human decomposition of figurative images. The results suggest that the human breakdowns follow well-known perceptual principles in particular the Gestalt laws.

AB - In this paper, we investigate human visual perception and establish a body of ground truth data elicited from human visual studies. We aim to build on the formative work of Ren, Eakins and Briggs who produced an initial ground truth database. Human participants were asked to draw and rank their perceptions of the,parts of a series of figurative images. These rankings were then used to score the perceptions, identify the preferred human breakdowns and thus allow us to induce perceptual rules for human decomposition of figurative images. The results suggest that the human breakdowns follow well-known perceptual principles in particular the Gestalt laws.

KW - PARTS

U2 - 10.1007/11788034_33

DO - 10.1007/11788034_33

M3 - Conference contribution

SN - 3-540-36018-2

SP - 320

EP - 329

BT - IMAGE AND VIDEO RETRIEVAL, PROCEEDINGS

A2 - Sundaram, H

A2 - Naphade, M

A2 - Smith, JR

A2 - Rui, Y

PB - Springer

CY - BERLIN

T2 - 5th International Conference on Image and Video Retrieval (CIVR 2006

Y2 - 13 July 2006 through 15 July 2006

ER -