This paper presents a database containing `ground truth' segmentations produced by humans for images of a wide variety of natural scenes. We define an error measure which quantifies the consistency between segmentations of differing granularities and find that different human segmentations of the same image are highly consistent. Use of this dataset is demonstrated in two applications: (1) evaluating the performance of segmentation algorithms and (2) measuring probability distributions associated with Gestalt grouping factors as well as statistics of image region properties
Описание
IEEE Xplore Abstract - A database of human segmented natural images and its application to evaluating segmentation algorith...
%0 Conference Paper
%1 937655
%A Martin, D.
%A Fowlkes, C.
%A Tal, D.
%A Malik, J.
%B Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on
%D 2001
%K benchmark database segmentation video
%P 416-423 vol.2
%R 10.1109/ICCV.2001.937655
%T A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
%U http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=937655
%V 2
%X This paper presents a database containing `ground truth' segmentations produced by humans for images of a wide variety of natural scenes. We define an error measure which quantifies the consistency between segmentations of differing granularities and find that different human segmentations of the same image are highly consistent. Use of this dataset is demonstrated in two applications: (1) evaluating the performance of segmentation algorithms and (2) measuring probability distributions associated with Gestalt grouping factors as well as statistics of image region properties
@inproceedings{937655,
abstract = {This paper presents a database containing `ground truth' segmentations produced by humans for images of a wide variety of natural scenes. We define an error measure which quantifies the consistency between segmentations of differing granularities and find that different human segmentations of the same image are highly consistent. Use of this dataset is demonstrated in two applications: (1) evaluating the performance of segmentation algorithms and (2) measuring probability distributions associated with Gestalt grouping factors as well as statistics of image region properties},
added-at = {2014-07-29T13:57:41.000+0200},
author = {Martin, D. and Fowlkes, C. and Tal, D. and Malik, J.},
biburl = {https://www.bibsonomy.org/bibtex/2052502333c76d300a86fce279aec231e/alex_ruff},
booktitle = {Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on},
description = {IEEE Xplore Abstract - A database of human segmented natural images and its application to evaluating segmentation algorith...},
doi = {10.1109/ICCV.2001.937655},
interhash = {baf41351e06bf6a4a4be3049a2d2e09c},
intrahash = {052502333c76d300a86fce279aec231e},
keywords = {benchmark database segmentation video},
pages = {416-423 vol.2},
timestamp = {2014-07-29T13:57:41.000+0200},
title = {A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=937655},
volume = 2,
year = 2001
}