A generalised feature for low level vision
This work presents an incremental improvement in low-level vision feature detection for computer vision researchers by generalizing several existing detection methods into a single framework.
This paper introduces the Sinclair-Town (ST) transform, a novel quantised transform that unifies edge, MSER-style region, and corner detection. The transform quantises the difference from the local mean into three values (dark-neutral-light) and naturally defines a local scale, providing a robust basis for image correspondence.
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.