| Título |
Computing the 2-D image Euler number by an artificial neural network |
| Tipo |
Congreso |
| Sub-tipo |
Memoria |
| Descripción |
2016 International Joint Conference on Neural Networks, IJCNN 2016 |
| Resumen |
We describe for the first time how the Euler number of a 2-D binary image can be obtained by means of Artificial Neural Network (ANN). Calculating the Euler image number is treated as a pattern classification problem. To arrive at the specialized ANN architecture, we perform a partial results analysis provided by a known formulation to compute the Euler image number. We use this analysis for designing the desired ANN architecture. Due to its good functioning characteristics, outcomes with the so-called Morphological Neural Perceptron with Dendritic Processing (MNPDP) are presented. Numerical as well as experimental results with realistic images to demonstrate the operation and applicability of the proposed approach are reported. Initial results concerning the GPU implementation of the proposed ANN to show that the processing time can be effectively reduced are also provided. |
| Observaciones |
DOI: 10.1109/IJCNN.2016.7727390 |
| Lugar |
Vancouver, BC |
| País |
Canada |
| No. de páginas |
1609-1616 |
| Vol. / Cap. |
|
| Inicio |
2016-07-24 |
| Fin |
2016-07-29 |
| ISBN/ISSN |
9781509006199 |
