Edge detection based on Hodgkin–Huxley neuron model simulation

In this paper, we propose a spiking neural network model for edge detection in images. The proposed model is biologically inspired by the mechanisms employed by natural vision systems, more specifically by the biologically fulfilled function of simple cells of the human primary visual cortex that ar...

Full description

Saved in:
Bibliographic Details
Published in:Cognitive processing 2017-08, Vol.18 (3), p.315-323
Main Authors: Yedjour, Hayat, Meftah, Boudjelal, Lézoray, Olivier, Benyettou, Abdelkader
Format: Article
Language:English
Subjects:
Artificial Intelligence
Behavioral Sciences
Biomedical and Life Sciences
Biomedicine
Computer Science
Computer Simulation
Humans
Image Processing
Models, Neurological
Neural Networks (Computer)
Neurons - physiology
Neurosciences
Orientation - physiology
Research Report
Vision, Ocular - physiology
Visual Cortex - physiology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a spiking neural network model for edge detection in images. The proposed model is biologically inspired by the mechanisms employed by natural vision systems, more specifically by the biologically fulfilled function of simple cells of the human primary visual cortex that are selective for orientation. Several aspects are studied in this model according to three characteristics: feedforward spiking neural structure; conductance-based model of the Hodgkin–Huxley neuron and Gabor receptive fields structure. A visualized map is generated using the firing rate of neurons representing the orientation map of the visual cortex area. We have simulated the proposed model on different images. Successful computer simulation results are obtained. For comparison, we have chosen five methods for edge detection. We finally evaluate and compare the performances of our model toward contour detection using a public dataset of natural images with associated contour ground truths. Experimental results show the ability and high performance of the proposed network model.
ISSN:1612-4782
1612-4790
DOI:10.1007/s10339-017-0803-z