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

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 seg- mentations of the same image are highly consistent. Use of this dataset is demonstrated in two applications: (1) eval- uating the performance of segmentation algorithms and (2) measuring probability distributions associated with Gestalt grouping factors as well as statistics of image region prop- erties.