ResearchBib Share Your Research, Maximize Your Social Impacts
注册免费获得最新研究资源 注册 >> 登录

FPGA IMPLEMENTATION OF ADAPTIVE INTEGRATED SPIKING NEURAL NETWORK FOR EFFICIENT IMAGE RECOGNITION SYSTEM

期刊名字: ICTACT Journal on Image and Video Processing (IJIVP) (Vol.4, No. 4)

Publication Date:

论文作者 : ; ; ;

起始页码 : 848-852

关键字 : Image Recognition; Spiking Neuron; FPGA; Artificial Neural Networks; Feature Extraction;

论文网址 : Downloadexternal 您也可以查找论文通过 : Google Scholarexternal

论文摘要

Image recognition is a technology which can be used in various applications such as medical image recognition systems, security, defense video tracking, and factory automation. In this paper we present a novel pipelined architecture of an adaptive integrated Artificial Neural Network for image recognition. In our proposed work we have combined the feature of spiking neuron concept with ANN to achieve the efficient architecture for image recognition. The set of training images are trained by ANN and target output has been identified. Real time videos are captured and then converted into frames for testing purpose and the image were recognized. The machine can operate at up to 40 frames/sec using images acquired from the camera. The system has been implemented on XC3S400 SPARTAN-3 Field Programmable Gate Arrays.

更新日期: 2014-07-21 16:31:55