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.
Keywords
Consistency (knowledge bases)Computer scienceSegmentationGround truthGestalt psychologyImage segmentationMeasure (data warehouse)Artificial intelligenceImage (mathematics)Pattern recognition (psychology)Natural (archaeology)Scene statisticsData miningAlgorithmGeography
Affiliated Institutions
Related Publications
SUN database: Large-scale scene recognition from abbey to zoo
Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases whi...
Publication Info
- Year
- 2002
- Type
- article
- Volume
- 2
- Pages
- 416-423
- Citations
- 7743
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
7743
OpenAlex
Cite This
David Martín,
Charless C. Fowlkes,
Doron Tal
et al.
(2002).
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics.
, 2
, 416-423.
https://doi.org/10.1109/iccv.2001.937655
Identifiers
- DOI
- 10.1109/iccv.2001.937655