Image Recognition Using Artificial Neural Networks with Particle Swarm Optimization Based on Hardware FPGA

Abstract

In this paper, a medical image recognition using Artificial Neural Networks (ANN) trained by Particle Swarm Optimization based on hardware implementation of Field Programmable Gate Array (FPGA) is presented, where the adaption of the Artificial Neural Network (ANN) weights using Particle Swarm Optimization (PSO) was proposed as a mechanism to improve the performance of ANN. Also in this paper, Hardware Design of ANN platform (HDANN) is proposed to evolve the architecture ANN circuits using FPGAspartan3
board (XSA-3S1000).
The HDANN design platform creates ANN design files using WebPACKTM ISE10.1 program, which are converted into device-dependent programming files for eventual downloading into FPGA device by using GXSLOAD program from the XSTOOLS programs.