A generalised feature for low level vision

TL;DR

This paper introduces the Sinclair-Town (ST) transform, a unified quantised transform for low-level vision tasks, enabling robust feature extraction and correspondence across images with potential for multi-scale and orientation adaptations.

Contribution

The paper proposes a novel, unified quantised transform that combines edge, region, and corner detection, and introduces methods for shape feature extraction and multi-scale analysis.

Findings

The ST transform effectively detects edges, regions, and corners within a single framework.

The transform facilitates robust image correspondence through shape feature extraction.

Multi-scale and asymmetric kernel behaviors enhance local feature detection.

Abstract

This papers presents a novel quantised transform (the Sinclair-Town or ST transform for short) that subsumes the rolls of both edge-detector, MSER style region detector and corner detector. The transform is similar to the $unsharp$ transform but the difference from the local mean is quantised to 3 values (dark-neutral-light). The transform naturally leads to the definition of an appropriate local scale. A range of methods for extracting shape features form the transformed image are presented. The generalized feature provides a robust basis for establishing correspondence between images. The transform readily admits more complicated kernel behaviour including multi-scale and asymmetric elements to prefer shorter scale or oriented local features.