The University of Edinburgh -
Division of Informatics
Forrest Hill & 80 South Bridge

Research Paper #912

Title:A Retina-like Image Representation of Primal Sketch Features Extracted using a Neural Network Approach
Authors:Gomes,HM; Fisher,RB; Hallam,JC
Date:May 1998
Presented:Accepted for publication in Noblesse Workshop on Non-Linear Model Based Image Analysis
Abstract:This paper presents a log-polar image representation composed of low-level features extracted using a connectionist approach. The low level features (edges, bars, blobs and ends) are based on Marr's primal sketch hypothesis for the human visual system [3] and are used as the entry point of an iconic vision system [1]. This unusual image representation has been created using a neural network that learns examples of the features in a window of receptive fields of the image representation.

[Search These Pages] [DAI Home Page] [Comment]