articleNov 13, 2002Closed access

A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics

DMDavid MartínCCCharless C. FowlkesDTDoron TalJMJitendra Malik

University of California, Berkeley

Indexed incrossref

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.

Citation impact

7,982
total citations
FWCI
78.78
Percentile
100%
References
18
Citations per year

Authors

4

Topics & keywords

Topics
Keywords
  • Consistency (knowledge bases)
  • Computer science
  • Segmentation
  • Ground truth
  • Gestalt psychology
  • Image segmentation
  • Measure (data warehouse)
  • Artificial intelligence
No related works found for this paper.

Funding