Abstract | ||
---|---|---|
Prior knowledge has been considered as valuable information in many image processing techniques. In this paper, we take the original image itself as the prior and develop a new fuzzy clustering algorithm for image segmentation by adding a new term to the objective function of Fuzzy C-means. The new term comes from Guided Filter for its capability of suppressing noise and preserving edge information. As a result, the calculation of memberships derived from the new objective incorporates the guidance information from the original image. In this way, the segmentation retains more subtle details of boundaries. According to experimental results, the proposed new method shows excellent performance in image segmentation tasks especially for the images with high noise rates. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/iFUZZY.2016.8004969 | 2016 International Conference on Fuzzy Theory and Its Applications (iFuzzy) |
Keywords | Field | DocType |
Fuzzy clustering method,Guided Filter,prior knowledge,edge information | Computer vision,Fuzzy clustering,Scale-space segmentation,Feature detection (computer vision),Pattern recognition,Image texture,Computer science,Segmentation-based object categorization,Image processing,Image segmentation,Artificial intelligence,Region growing | Journal |
Volume | Issue | ISSN |
19 | 6 | 2377-5823 |
ISBN | Citations | PageRank |
978-1-5090-4112-1 | 9 | 0.48 |
References | Authors | |
21 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Li Guo | 1 | 58 | 18.35 |
Long Chen | 2 | 528 | 49.21 |
Yingwen Wu | 3 | 9 | 0.48 |
C. L. Philip Chen | 4 | 4022 | 244.76 |