Primal sketch feature extraction from a log-polar image

Primal-Sketch Feature Extraction from a Log-Polar Images

We present a novel approach 1 for extracting primal sketch features (edges, bars, blobs and ends) from a log-polar image. Symmetry operators and a PCA pre-processing module precede a set of neural networks that learn the feature’s class and contrast. Experiments show the process accurately extracts the desired feature-based image description.

An Architecture for Primal-Sketch Feature Extraction in a Log-Polar Representation

Model Learning in Iconic Vision

Generally, object recognition research falls into three main categories: (a) geometric, symbolic or structure based recognition, which is usually associated with CAD-based vision and 3-D object recognition; (b) property, vector or feature based recognition, involving techniques that vary from specific feature vectors, multiple filtering to global descriptors for shape, texture and colour; and (...

Learning-Based versus Model-Based Log-Polar Feature Extraction Operators: A Comparative Study

In this paper, we compare two distinct primal sketch feature extraction operators: one based on neural network feature learning and the other based on mathematical models of the features. We tested both kinds of operator with a set of known, but previously untrained, synthetic features and, while varying their classification thresholds, measured the operator’s false acceptance and false rejecti...

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 [10]. The feature extraction process used a neural network that learns examples of the features in a window of rece...