Normalized Joint Mutual Information Measure for Ground Truth Based Segmentation Evaluation
Summary :
Ground truth based image segmentation evaluation paradigm plays an important role in objective evaluation of segmentation algorithms. So far, many evaluation methods in terms of comparing clusterings in machine learning field have been developed. However, most traditional pairwise similarity measures, which only compare a machine generated clustering to a “true” clustering, have their limitations in some cases, e.g. when multiple ground truths are available for the same image. In this letter, we propose utilizing an information theoretic measure, named NJMI (Normalized Joint Mutual Information), to handle the situations which the pairwise measures can not deal with. We illustrate the effectiveness of NJMI for both unsupervised and supervised segmentation evaluation.
- Publication
- IEICE TRANSACTIONS on Information Vol.E95-D No.10 pp.2581-2584
- Publication Date
- 2012/10/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E95.D.2581
- Type of Manuscript
- LETTER
- Category
- Image Recognition, Computer Vision
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Xue BAI, Yibiao ZHAO, Siwei LUO, "Normalized Joint Mutual Information Measure for Ground Truth Based Segmentation Evaluation" in IEICE TRANSACTIONS on Information,
vol. E95-D, no. 10, pp. 2581-2584, October 2012, doi: 10.1587/transinf.E95.D.2581.
Abstract: Ground truth based image segmentation evaluation paradigm plays an important role in objective evaluation of segmentation algorithms. So far, many evaluation methods in terms of comparing clusterings in machine learning field have been developed. However, most traditional pairwise similarity measures, which only compare a machine generated clustering to a “true” clustering, have their limitations in some cases, e.g. when multiple ground truths are available for the same image. In this letter, we propose utilizing an information theoretic measure, named NJMI (Normalized Joint Mutual Information), to handle the situations which the pairwise measures can not deal with. We illustrate the effectiveness of NJMI for both unsupervised and supervised segmentation evaluation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.2581/_p
Copy
@ARTICLE{e95-d_10_2581,
author={Xue BAI, Yibiao ZHAO, Siwei LUO, },
journal={IEICE TRANSACTIONS on Information},
title={Normalized Joint Mutual Information Measure for Ground Truth Based Segmentation Evaluation},
year={2012},
volume={E95-D},
number={10},
pages={2581-2584},
abstract={Ground truth based image segmentation evaluation paradigm plays an important role in objective evaluation of segmentation algorithms. So far, many evaluation methods in terms of comparing clusterings in machine learning field have been developed. However, most traditional pairwise similarity measures, which only compare a machine generated clustering to a “true” clustering, have their limitations in some cases, e.g. when multiple ground truths are available for the same image. In this letter, we propose utilizing an information theoretic measure, named NJMI (Normalized Joint Mutual Information), to handle the situations which the pairwise measures can not deal with. We illustrate the effectiveness of NJMI for both unsupervised and supervised segmentation evaluation.},
keywords={},
doi={10.1587/transinf.E95.D.2581},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Normalized Joint Mutual Information Measure for Ground Truth Based Segmentation Evaluation
T2 - IEICE TRANSACTIONS on Information
SP - 2581
EP - 2584
AU - Xue BAI
AU - Yibiao ZHAO
AU - Siwei LUO
PY - 2012
DO - 10.1587/transinf.E95.D.2581
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2012
AB - Ground truth based image segmentation evaluation paradigm plays an important role in objective evaluation of segmentation algorithms. So far, many evaluation methods in terms of comparing clusterings in machine learning field have been developed. However, most traditional pairwise similarity measures, which only compare a machine generated clustering to a “true” clustering, have their limitations in some cases, e.g. when multiple ground truths are available for the same image. In this letter, we propose utilizing an information theoretic measure, named NJMI (Normalized Joint Mutual Information), to handle the situations which the pairwise measures can not deal with. We illustrate the effectiveness of NJMI for both unsupervised and supervised segmentation evaluation.
ER -
English
