FPGA IMPLEMENTATION OF ADAPTIVE INTEGRATED SPIKING NEURAL NETWORK FOR EFFICIENT IMAGE RECOGNITION SYSTEM
Journal: ICTACT Journal on Image and Video Processing (IJIVP) (Vol.4, No. 4)Publication Date: 2014-05-01
Authors : T. Pasupathi; A. Arockia Bazil Raj; J. Arputhavijayaselvi;
Page : 848-852
Keywords : Image Recognition; Spiking Neuron; FPGA; Artificial Neural Networks; Feature Extraction;
Abstract
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.
Other Latest Articles
- THE IMPACT OF SOCIAL INEQUALITY ON HEALTH OF STUDENTS IN HIGHER EDUCATION INSTITUTIONS
- REDUCING RUN-TIME FOR MOVING OBJECT DETECTION IN BACKGROUND BUFFERING APPROACH
- THE TAT-TEST IN DIAGNOSTICS OF FEATURES OF THE PERSONALITY
- A PERFORMANCE COMPARISON ON DIFFERENTIAL PREDICTION BASED ALGORITHMS IN H.264/AVC
- ADAPTIVE BEHAVIOUR AS INDICATOR OF PSYCHOLOGICAL MATURING OF PERSONALITY
Last modified: 2014-07-21 16:31:55