Brain Image Segmentation Based on FCM Clustering Algorithm and Rough Set
In this paper, a new image segmentation method is proposed by combining the FCM clustering algorithm with a rough set theory. First, the attribute value table is constructed based on the segmentation results of FCM under different clustering numbers, and the image is divided into several small regio...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8612906/ |
| _version_ | 1818645010214551552 |
|---|---|
| author | Hong Huang Fanzhi Meng Shaohua Zhou Feng Jiang Gunasekaran Manogaran |
| author_facet | Hong Huang Fanzhi Meng Shaohua Zhou Feng Jiang Gunasekaran Manogaran |
| author_sort | Hong Huang |
| collection | DOAJ |
| description | In this paper, a new image segmentation method is proposed by combining the FCM clustering algorithm with a rough set theory. First, the attribute value table is constructed based on the segmentation results of FCM under different clustering numbers, and the image is divided into several small regions based on the indistinguishable relationship of attributes. Then, the weight values of each attribute are obtained by value reduction and used as the basis to calculate the difference between regions and then the similarity evaluation of each region is realized through the equivalence relationship defined by the difference degree. Finally, the final equivalence relation defined by similarity is used to merge regions and complete image segmentation. This method is validated in the segmentation of artificially generated images, brain CT images, and MRI images. The experimental results show that compared with the FCM method, the proposed method can reduce the error rate and achieve better segmentation results for the fuzzy boundary region. And, the experimental results also prove that the algorithm has strong anti-noise ability. |
| first_indexed | 2024-12-17T00:23:56Z |
| format | Article |
| id | doaj.art-85678b78afbd41019e2ddcd3427bc024 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T00:23:56Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-85678b78afbd41019e2ddcd3427bc0242022-12-21T22:10:30ZengIEEEIEEE Access2169-35362019-01-017123861239610.1109/ACCESS.2019.28930638612906Brain Image Segmentation Based on FCM Clustering Algorithm and Rough SetHong Huang0Fanzhi Meng1Shaohua Zhou2https://orcid.org/0000-0002-0973-7231Feng Jiang3https://orcid.org/0000-0001-8342-1211Gunasekaran Manogaran4https://orcid.org/0000-0003-4083-6163School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, ChinaInstitute of Computer Application, China Academy of Engineering Physics, Mianyang, ChinaSchool of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, ChinaSchool of Computer, Harbin Institute of Technology, Harbin, ChinaJohn Muir Institute of the Environment, University of California at Davis, Davis, CA, USAIn this paper, a new image segmentation method is proposed by combining the FCM clustering algorithm with a rough set theory. First, the attribute value table is constructed based on the segmentation results of FCM under different clustering numbers, and the image is divided into several small regions based on the indistinguishable relationship of attributes. Then, the weight values of each attribute are obtained by value reduction and used as the basis to calculate the difference between regions and then the similarity evaluation of each region is realized through the equivalence relationship defined by the difference degree. Finally, the final equivalence relation defined by similarity is used to merge regions and complete image segmentation. This method is validated in the segmentation of artificially generated images, brain CT images, and MRI images. The experimental results show that compared with the FCM method, the proposed method can reduce the error rate and achieve better segmentation results for the fuzzy boundary region. And, the experimental results also prove that the algorithm has strong anti-noise ability.https://ieeexplore.ieee.org/document/8612906/Brain image segmentationFCM clusteringrough setsystem |
| spellingShingle | Hong Huang Fanzhi Meng Shaohua Zhou Feng Jiang Gunasekaran Manogaran Brain Image Segmentation Based on FCM Clustering Algorithm and Rough Set IEEE Access Brain image segmentation FCM clustering rough set system |
| title | Brain Image Segmentation Based on FCM Clustering Algorithm and Rough Set |
| title_full | Brain Image Segmentation Based on FCM Clustering Algorithm and Rough Set |
| title_fullStr | Brain Image Segmentation Based on FCM Clustering Algorithm and Rough Set |
| title_full_unstemmed | Brain Image Segmentation Based on FCM Clustering Algorithm and Rough Set |
| title_short | Brain Image Segmentation Based on FCM Clustering Algorithm and Rough Set |
| title_sort | brain image segmentation based on fcm clustering algorithm and rough set |
| topic | Brain image segmentation FCM clustering rough set system |
| url | https://ieeexplore.ieee.org/document/8612906/ |
| work_keys_str_mv | AT honghuang brainimagesegmentationbasedonfcmclusteringalgorithmandroughset AT fanzhimeng brainimagesegmentationbasedonfcmclusteringalgorithmandroughset AT shaohuazhou brainimagesegmentationbasedonfcmclusteringalgorithmandroughset AT fengjiang brainimagesegmentationbasedonfcmclusteringalgorithmandroughset AT gunasekaranmanogaran brainimagesegmentationbasedonfcmclusteringalgorithmandroughset |