A Learning-Based Framework for Supervised and Unsupervised Image Segmentation Evaluation
A Learning-Based Framework for Supervised and Unsupervised Image Segmentation Evaluation
复制标题
用于监督和无监督图像分割评估的基于学习的框架
DOI:
10.1142/s0219467814500144
复制
发表时间:
2014-08
影响因子:
1.6
通讯作者:
Tianrui Li
中科院分区:
文献类型:
--
作者:
Jian Lin;Bo Peng;Tianrui Li
Image segmentation is a fundamental task in automatic image analysis. However, there is still no generally accepted effectiveness measure which is suitable for evaluating the segmentation quality in every application. In this paper, we propose an evaluation framework which benefits from multiple stand-alone measures. To this end, different segmentation evaluation measures are chosen to evaluate segmentation separately, and the results are effectively combined using machine learning methods. We train and implement this framework in our brand-new segmentation dataset which contains images of different contents with segmentation ground truth and Weizmann segmentation database (WSD). In addition, we provide human evaluation of image segmentation pairs to benchmark the evaluation results of the measures. Experimental results show a better performance than the stand-alone methods.
登录
查看更多内容
DOI:
10.1504/ijguc.2012.045710
发表时间:
2012-03
期刊:
Int. J. Grid Util. Comput.
影响因子:
--
作者:
Lugang Zhao;Chengke Wu
通讯作者:
Lugang Zhao;Chengke Wu
DOI:
10.1109/tpami.2011.130
发表时间:
2012-02-01
影响因子:
23.6
作者:
Alpert, Sharon;Galun, Meirav;Basri, Ronen
通讯作者:
Basri, Ronen
影响因子:
7.5
作者:
Schapire, RE;Singer, Y
通讯作者:
Singer, Y
影响因子:
10.6
作者:
Grigorescu, SE;Petkov, N;Kruizinga, P
通讯作者:
Kruizinga, P
DOI:
10.1007/3-540-47977-5_27
发表时间:
2002-01-01
期刊:
COMPUTER VISION - ECCV 2002 PT III
影响因子:
--
作者:
Freixenet, J;Muñoz, X;Cufí, X
通讯作者:
Cufí, X