Initialization Methods For Conventional Fuzzy C-Means And Its Application Towards Colour Image Segmentation
Due to its capability in providing a particularly promising solution to clustering problems, the conventional Fuzzy C-Mean (FCM) algorithm is widely used as a segmentation method. However, it is very sensitive to the initialization conditions of number of clusters and initial cluster centres. Thus,...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://eprints.usm.my/42775/ http://eprints.usm.my/42775/1/TAN_KHANG_SIANG.pdf |
| _version_ | 1848879653316460544 |
|---|---|
| author | Tan , Khang Siang |
| author_facet | Tan , Khang Siang |
| author_sort | Tan , Khang Siang |
| building | USM Institutional Repository |
| collection | Online Access |
| description | Due to its capability in providing a particularly promising solution to clustering problems, the conventional Fuzzy C-Mean (FCM) algorithm is widely used as a segmentation method. However, it is very sensitive to the initialization conditions of number of clusters and initial cluster centres. Thus, three initialization schemes for the conventional FCM algorithm namely the Hierarchical Approach (HA), the Colour Quantization (CQ) and the Histogram Thresholding (HT) are proposed to automatically obtain the initialization conditions for the conventional FCM algorithm. |
| first_indexed | 2025-11-15T17:50:39Z |
| format | Thesis |
| id | usm-42775 |
| institution | Universiti Sains Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T17:50:39Z |
| publishDate | 2011 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | usm-427752019-04-12T05:26:37Z http://eprints.usm.my/42775/ Initialization Methods For Conventional Fuzzy C-Means And Its Application Towards Colour Image Segmentation Tan , Khang Siang TK1-9971 Electrical engineering. Electronics. Nuclear engineering Due to its capability in providing a particularly promising solution to clustering problems, the conventional Fuzzy C-Mean (FCM) algorithm is widely used as a segmentation method. However, it is very sensitive to the initialization conditions of number of clusters and initial cluster centres. Thus, three initialization schemes for the conventional FCM algorithm namely the Hierarchical Approach (HA), the Colour Quantization (CQ) and the Histogram Thresholding (HT) are proposed to automatically obtain the initialization conditions for the conventional FCM algorithm. 2011-05 Thesis NonPeerReviewed application/pdf en http://eprints.usm.my/42775/1/TAN_KHANG_SIANG.pdf Tan , Khang Siang (2011) Initialization Methods For Conventional Fuzzy C-Means And Its Application Towards Colour Image Segmentation. Masters thesis, Universiti Sains Malaysia. |
| spellingShingle | TK1-9971 Electrical engineering. Electronics. Nuclear engineering Tan , Khang Siang Initialization Methods For Conventional Fuzzy C-Means And Its Application Towards Colour Image Segmentation |
| title | Initialization Methods For Conventional Fuzzy C-Means And Its Application Towards Colour Image Segmentation |
| title_full | Initialization Methods For Conventional Fuzzy C-Means And Its Application Towards Colour Image Segmentation |
| title_fullStr | Initialization Methods For Conventional Fuzzy C-Means And Its Application Towards Colour Image Segmentation |
| title_full_unstemmed | Initialization Methods For Conventional Fuzzy C-Means And Its Application Towards Colour Image Segmentation |
| title_short | Initialization Methods For Conventional Fuzzy C-Means And Its Application Towards Colour Image Segmentation |
| title_sort | initialization methods for conventional fuzzy c-means and its application towards colour image segmentation |
| topic | TK1-9971 Electrical engineering. Electronics. Nuclear engineering |
| url | http://eprints.usm.my/42775/ http://eprints.usm.my/42775/1/TAN_KHANG_SIANG.pdf |