Learning and extracting primal-sketch features in a log-polar image representation

This paper presents a novel and more successful learning based approach to extracting low level features in a retina-like (log-polar) image representation. The low level features (edges, bars, blobs and ends) are based on Marr´s primal sketch hypothesis for the human visual system. The feature extraction process used a neural network that learns examples of the features in a window of receptive fields of the image representation. An architecture designed to encode the feature´s class, position, orientation and contrast has been proposed and tested. Success depended on the incorporation of a function to normalise the feature´s orientation and a PCA pre-processing module to produce better separation in the feature space