FPGA IMPLEMENTATION OF ADAPTIVE INTEGRATED SPIKING NEURAL NETWORK FOR EFFICIENT IMAGE RECOGNITION SYSTEM
| Autor: | Arockia Bazil Raj A, Arputhavijayaselvi J, T. Pasupathi |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
Spiking neural network
Image Recognition business.industry Time delay neural network Computer science Real-time computing ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION lcsh:Computer applications to medicine. Medical informatics Feature Extraction lcsh:Telecommunication Spiking Neuron lcsh:TK5101-6720 lcsh:R858-859.7 Artificial intelligence business Field-programmable gate array FPGA Artificial Neural Networks |
| Zdroj: | ICTACT Journal on Image and Video Processing, Vol 4, Iss 4, Pp 848-852 (2014) |
| ISSN: | 0976-9102 0976-9099 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|