Name
Title | ||
|---|---|---|
Determination of the optimal number of clusters using a spectral clustering optimization. |
Abstract | ||
|---|---|---|
In this paper, we present a new method, called Spectral Global Silhouette method (GS), to calculate the optimal number of clusters in a dataset using a Spectral Clustering algorithm. It combines both a Silhouette Validity Index and the concept of Local Scaling. First, the GS algorithm has first been tested using synthetic data. Then, it is applied on real data for image segmentation task. In addition, three new methods for image segmentation and two new ways to calculate the optimal number of groups in an image are proposed. Our experiments have shown a promising performance of the proposed algorithms. A new approach to find the optimal number of clusters is presented.This approach is used for the Spectral Clustering algorithm.The method is tested using synthetic data and images.Two ways to calculate the optimal number of groups in an image are presented.Three methods for image segmentation are proposed. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1016/j.eswa.2016.08.059 | Expert Systems with Applications |
Keywords | Field | DocType |
Spectral clustering,Optimal number of clusters,Silhouette Index,Local scaling,Image segmentation | Spectral clustering,Scale-space segmentation,Pattern recognition,Correlation clustering,Computer science,Silhouette,Segmentation-based object categorization,Determining the number of clusters in a data set,Image segmentation,Synthetic data,Artificial intelligence,Machine learning | Journal |
Volume | Issue | ISSN |
65 | C | 0957-4174 |
Citations | PageRank | References |
8 | 0.48 | 11 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Angel Mur | 1 | 13 | 2.05 |
| R. Dormido | 2 | 90 | 10.76 |
| N. Duro | 3 | 98 | 13.59 |
| S. Dormido-Canto | 4 | 173 | 17.58 |
| Jesús Vega | 5 | 8 | 0.48 |