Name
Abstract | ||
|---|---|---|
This work presents the design of a real-time system to model visual objects with the use of self-organising networks. The architecture of the system addresses multiple computer vision tasks such as image segmentation, optimal parameter estimation and object representation. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. We present experimental results for hands and faces, and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product. The proposed method is easily extensible to 3D objects, as it offers similar features for efficient mesh reconstruction. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1007/s00521-016-2579-y | Neural Computing and Applications |
Keywords | Field | DocType |
Clustering,Minimum description length,Self-organising networks,Shape modelling | Computer vision,Visual Objects,Computer science,Topographic map,Minimum description length,Image segmentation,Artificial intelligence,Overfitting,Estimation theory,Cluster analysis,Neural gas,Machine learning | Journal |
Volume | Issue | ISSN |
29 | 10 | 1433-3058 |
Citations | PageRank | References |
1 | 0.35 | 20 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Anastassia Angelopoulou | 1 | 102 | 21.29 |
| José Garcia Rodriguez | 2 | 55 | 9.71 |
| Sergio Orts-Escolano | 3 | 313 | 29.45 |
| Gaurav Gupta | 4 | 14 | 7.06 |
| Alexandra Psarrou | 5 | 199 | 27.14 |