A Retina-like Image Representation of Primal Sketch Features Extracted using a Neural Network Approach

摘要

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.