A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference(2001)
摘要
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.
更多查看译文
关键词
computer vision,image segmentation,visual databases,Gestalt grouping factors,ground truth,image database,image region properties,natural scenes,performance of segmentation,probability distributions,segmentations
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要