A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics

David R. Martin, Charless Fowlkes, Doron Tal and Jitendra Malik

EECS Department
University of California, Berkeley
Technical Report No. UCB/CSD-01-1133
January 2001

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2001/CSD-01-1133.pdf

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.


BibTeX citation:

@techreport{Martin:CSD-01-1133,
    Author = {Martin, David R. and Fowlkes, Charless and Tal, Doron and Malik, Jitendra},
    Title = {A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2001},
    Month = {Jan},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2001/6434.html},
    Number = {UCB/CSD-01-1133},
    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.}
}

EndNote citation:

%0 Report
%A Martin, David R.
%A Fowlkes, Charless
%A Tal, Doron
%A Malik, Jitendra
%T A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics
%I EECS Department, University of California, Berkeley
%D 2001
%@ UCB/CSD-01-1133
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2001/6434.html
%F Martin:CSD-01-1133