Image boundary detection or image segmentation is an important step in image analysis. However, choosing appropriate parameters for boundary detection algorithms is necessary to achieve good boundary detection results. Image boundary detection fusion with unsupervised parameters can output a final consensus boundary, which is generally better than using unsupervised or supervised image boundary detection algorithms. In this study, we theoretically examine why image boundary detection fusion can work well and we propose a mixture model for image boundary detection fusion (MMIBDF) to achieve good consensus segmentation in an unsupervised manner. All of the segmentation algorithms are treated as new features and the segmentation results obtained by the algorithms are the values of the new features. The MMIBDF is designed to sample the boundary according to a discrete distribution. We present an inference method for MMIBDF and describe the corresponding algorithm in detail. Extensive empirical results demonstrate that MMIBDF significantly outperforms other image boundary detection fusion algorithms and the base image boundary detection algorithms according to most performance indices.
Yinghui ZHANG
Northeastern University
Hongjun WANG
Southwest Jiaotong University
Hengxue ZHOU
Southwest Jiaotong University
Ping DENG
Southwest Jiaotong University
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.
Copy
Yinghui ZHANG, Hongjun WANG, Hengxue ZHOU, Ping DENG, "A Mixture Model for Image Boundary Detection Fusion" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 4, pp. 1159-1166, April 2018, doi: 10.1587/transinf.2017EDP7314.
Abstract: Image boundary detection or image segmentation is an important step in image analysis. However, choosing appropriate parameters for boundary detection algorithms is necessary to achieve good boundary detection results. Image boundary detection fusion with unsupervised parameters can output a final consensus boundary, which is generally better than using unsupervised or supervised image boundary detection algorithms. In this study, we theoretically examine why image boundary detection fusion can work well and we propose a mixture model for image boundary detection fusion (MMIBDF) to achieve good consensus segmentation in an unsupervised manner. All of the segmentation algorithms are treated as new features and the segmentation results obtained by the algorithms are the values of the new features. The MMIBDF is designed to sample the boundary according to a discrete distribution. We present an inference method for MMIBDF and describe the corresponding algorithm in detail. Extensive empirical results demonstrate that MMIBDF significantly outperforms other image boundary detection fusion algorithms and the base image boundary detection algorithms according to most performance indices.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7314/_p
Copy
@ARTICLE{e101-d_4_1159,
author={Yinghui ZHANG, Hongjun WANG, Hengxue ZHOU, Ping DENG, },
journal={IEICE TRANSACTIONS on Information},
title={A Mixture Model for Image Boundary Detection Fusion},
year={2018},
volume={E101-D},
number={4},
pages={1159-1166},
abstract={Image boundary detection or image segmentation is an important step in image analysis. However, choosing appropriate parameters for boundary detection algorithms is necessary to achieve good boundary detection results. Image boundary detection fusion with unsupervised parameters can output a final consensus boundary, which is generally better than using unsupervised or supervised image boundary detection algorithms. In this study, we theoretically examine why image boundary detection fusion can work well and we propose a mixture model for image boundary detection fusion (MMIBDF) to achieve good consensus segmentation in an unsupervised manner. All of the segmentation algorithms are treated as new features and the segmentation results obtained by the algorithms are the values of the new features. The MMIBDF is designed to sample the boundary according to a discrete distribution. We present an inference method for MMIBDF and describe the corresponding algorithm in detail. Extensive empirical results demonstrate that MMIBDF significantly outperforms other image boundary detection fusion algorithms and the base image boundary detection algorithms according to most performance indices.},
keywords={},
doi={10.1587/transinf.2017EDP7314},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - A Mixture Model for Image Boundary Detection Fusion
T2 - IEICE TRANSACTIONS on Information
SP - 1159
EP - 1166
AU - Yinghui ZHANG
AU - Hongjun WANG
AU - Hengxue ZHOU
AU - Ping DENG
PY - 2018
DO - 10.1587/transinf.2017EDP7314
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2018
AB - Image boundary detection or image segmentation is an important step in image analysis. However, choosing appropriate parameters for boundary detection algorithms is necessary to achieve good boundary detection results. Image boundary detection fusion with unsupervised parameters can output a final consensus boundary, which is generally better than using unsupervised or supervised image boundary detection algorithms. In this study, we theoretically examine why image boundary detection fusion can work well and we propose a mixture model for image boundary detection fusion (MMIBDF) to achieve good consensus segmentation in an unsupervised manner. All of the segmentation algorithms are treated as new features and the segmentation results obtained by the algorithms are the values of the new features. The MMIBDF is designed to sample the boundary according to a discrete distribution. We present an inference method for MMIBDF and describe the corresponding algorithm in detail. Extensive empirical results demonstrate that MMIBDF significantly outperforms other image boundary detection fusion algorithms and the base image boundary detection algorithms according to most performance indices.
ER -