A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
2002Vol. 2, pp. 416–423
Citations Over TimeTop 1% of 2002 papers
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.
Related Papers
- → LOGOTYPE TASARIMINDA GESTALT GÖRSEL ALGI KURAMININ ETKİLERİ(2020)3 cited
- → Perception, Gestalt Principles of(2005)2 cited
- Form perception: An Interactive guide to the Gestalt principles(2010)
- Heterogeneous Isomorphism in Art Design(2005)
- → Gestalt Laws and Perceptual Organization(2023)