1. Fast 2D/3D object representation with growing neural gas
- Author
-
Alexandra Psarrou, José García Rodríguez, Gaurav Gupta, Anastassia Angelopoulou, Sergio Orts-Escolano, Universidad de Alicante. Departamento de Tecnología Informática y Computación, Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial, Informática Industrial y Redes de Computadores, and Robótica y Visión Tridimensional (RoViT)
- Subjects
0209 industrial biotechnology ,Neural gas ,Computer science ,02 engineering and technology ,Overfitting ,Clustering ,020901 industrial engineering & automation ,Artificial Intelligence ,Visual Objects ,0202 electrical engineering, electronic engineering, information engineering ,Computer vision ,Cluster analysis ,Representation (mathematics) ,Self-organising networks ,computer.programming_language ,business.industry ,Minimum description length ,Ciencia de la Computación e Inteligencia Artificial ,Image segmentation ,Object (computer science) ,Shape modelling ,Original Article ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,Arquitectura y Tecnología de Computadores ,computer ,Software - 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. This work was partially funded by the Spanish Government DPI2013-40534-R Grant.
- Published
- 2016
- Full Text
- View/download PDF