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

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.

DOI: 10.1109/ICCV.2001.937655

Extracted Key Phrases

14 Figures and Tables

0200400'02'04'06'08'10'12'14'16
Citations per Year

3,492 Citations

Semantic Scholar estimates that this publication has 3,492 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Martin2001ADO, title={A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics}, author={David R. Martin and Charless C. Fowlkes and Doron Tal and Jitendra Malik}, booktitle={ICCV}, year={2001} }