UCL Discovery

Abstract

We report progress on an approach (Geometric Texton Theory - GTT) that like Marr's 'primal sketch' aims to describe image structure in a way that emphasises its qualitative aspects. In both approaches, image description is by labelling points using a vocabulary of feature types, though compared to Marr we aim for a much larger feature vocabulary.We base GTT on the Gaussian derivative (DtG) model of V I measurement. Marr's primal sketch was based on DtG filters of derivative order up to 2(nd), for GTT we plan to extend to the physiologically plausible limit of 4(th). This is how we will achieve a larger feature vocabulary (we estimate 30-150) than Marr's 'edge', 'line' and 'blob'. The central requirement of GTT then is for a procedure for determining the feature vocabulary that will scale up to 4(th) order. We have previously published feature category systems for 1-D 1(st) order, 1-D 2(nd) order, 2-D 1(st) order and 2-D pure 2(nd) order. In this paper we will present results of GTT as applied to 2-D mixed 1(st) + 2(nd) order features.We will review various approaches to defining the feature vocabulary, including ones based on (i) purely geometrical considerations, and (ii) natural image statistics.