Sistema basado en FPGA para la evaluación de redes neuronales orientadas al reconocimiento de imágenes

This paper presents the use of Field Programmable Gate Arrays (FPGA) to evaluate an Artificial Neural Network (ANN) system, and also to apply image pattern recognition to alphabetic characters in contexts where different neural network models are utilized. This is performed in order to evaluate the performance of the neural networks implemented in the FPGA and also to analyze the Spartan-3 FPGA XCS200 performance. This study has four phases: neural network model selection; development of a training platform using Labview RNA; design, implementation and verification of RNA models; and parameter setup to evaluate RNA Spartan-3 FPGA XCS200 performance.