A new challenging image dataset with simple background for evaluating and developing co-segmentation algorithms

Mengqiao Yu, Xiabi Liu*, Murong Wang, Guanghui Han

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

摘要

Many image co-segmentation algorithms have been proposed over the last decade. In this paper, we present a new dataset for evaluating co-segmentation algorithms, which contains 889 image groups with 18 images in each and the pixel-wise hand-annotated ground truths. The dataset is characterized by simple background produced from nearly a single color. It looks simple but is actually very challenging for current co-segmentation algorithms, because of four difficult cases in it: easy-confused foreground with background, transparent regions in objects, minor holes in objects, and shadows. In order to test the usefulness of our dataset, we review the state-of-the-art co-segmentation algorithms and evaluate seven algorithms on our dataset. The obtained performance of each algorithm is compared with those previously reported in the datasets with complex background. The results prove that our dataset is valuable for the development of co-segmentation techniques. It is more feasible to solve the four difficulties above on the simple background and then extend the solutions to the complex background problems. Our dataset can be freely downloaded from: http://www.iscbit.org/source/MLMR-COS.zip.

源语言英语
文章编号115813
期刊Signal Processing: Image Communication
83
DOI
出版状态已出版 - 4月 2020

指纹

探究 'A new challenging image dataset with simple background for evaluating and developing co-segmentation algorithms' 的科研主题。它们共同构成独一无二的指纹。

引用此

Yu, M., Liu, X., Wang, M., & Han, G. (2020). A new challenging image dataset with simple background for evaluating and developing co-segmentation algorithms. Signal Processing: Image Communication, 83, 文章 115813. https://doi.org/10.1016/j.image.2020.115813