Title |
Fast 2D/3D object representation with growing neural gas
|
---|---|
Published in |
Neural Computing and Applications, September 2016
|
DOI | 10.1007/s00521-016-2579-y |
Pubmed ID | |
Authors |
Anastassia Angelopoulou, Jose Garcia Rodriguez, Sergio Orts-Escolano, Gaurav Gupta, Alexandra Psarrou |
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. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
Spain | 1 | 100% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 1 | 100% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 18 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 4 | 22% |
Professor > Associate Professor | 3 | 17% |
Student > Doctoral Student | 2 | 11% |
Student > Master | 2 | 11% |
Student > Ph. D. Student | 1 | 6% |
Other | 2 | 11% |
Unknown | 4 | 22% |
Readers by discipline | Count | As % |
---|---|---|
Computer Science | 10 | 56% |
Engineering | 3 | 17% |
Neuroscience | 1 | 6% |
Unknown | 4 | 22% |