By Topic

Modelling the visual cortex using artificial neural networks for visual image reconstruction

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $33
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
G. Qiu ; Derby Univ., UK

Presents an artificial neural network model with some special neurons that are designed to function as the feature detectors found in the visual cortex, and applies it to the reconstruction of visual images. The model is a multilayer feedforward neural network. The neurons in the first hidden layer of the network are feature detectors of various scales and orientations. The connection strengths between the input and the first hidden layer are pre-set (and fixed) such that the outputs of this layer are some visually important features of various scales. The rest of the connection strengths in the network are decided through learning via the backpropagation algorithm in a self-supervising manner. Computer simulations were conducted, and the results seem to show that the artificial neural network model proposed in this paper is consistent with its biological counterpart (the visual cortex) in terms of the visual features detected by its feature detectors and its ability to reconstruct near-perfect input images from the output of these feature detectors. It is also shown that the system can be used for effective image data compression. Simulation results are presented which show promising potential of the new system for image coding applications

Published in:

Artificial Neural Networks, 1995., Fourth International Conference on

Date of Conference:

26-28 Jun 1995