Fast Image Representation with GPU-Based Growing Neural Gas

This paper aims to address the ability of self-organizing neural network models to manage real-time applications. Specifically, we introduce a Graphics Processing Unit (GPU) implementation with Compute Unified Device Architecture (CUDA) of the Growing Neural Gas (GNG) network. The Growing Neural Gas network with its attributes of growth, flexibility, rapid adaptation, and excellent quality representation of the input space makes it a suitable model for real time applications. In contrast to existing algorithms the proposed GPU implementation allow the acceleration keeping good quality of representation. Comparative experiments using iterative, parallel and hybrid implementation are carried out to demonstrate the effectiveness of CUDA implementation in representing linear and non-linear input spaces under time restrictions.

[1]  Thomas Martinetz,et al.  Topology representing networks , 1994, Neural Networks.

[2]  Anath Fischer,et al.  Three-dimensional surface reconstruction using meshing growing neural gas (MGNG) , 2008, The Visual Computer.

[3]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[4]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[5]  Soo-Chang Pei,et al.  Color image segmentation using local histogram and self-organization of Kohonen feature map , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[6]  T. Martínez,et al.  Competitive Hebbian Learning Rule Forms Perfectly Topology Preserving Maps , 1993 .

[7]  Pragya Agarwal,et al.  Self-Organising Maps , 2008 .

[8]  José García Rodríguez,et al.  Representation of 2D Objects with a Topology Preserving Network , 2002, PRIS.

[9]  Heung-Won Park,et al.  Image segmentation of color image based on region coherency , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).