A Unified Framework for Salient Curves, Regions, and Junctions Inference

We present a unified computational framework to generate descriptions in terms of regions, curves, and labelled junctions, from sparse, noisy, binary data in 2-D. Each input site can be a point, a point with an associated tangent direction, a point with an associated tangent vector, or any combination of the above. The methodology is grounded on two elements: tensor calculus for representation, and non-linear voting for communication. Each input site communicates its information (a tensor) to its neighborhood through a predefined (tensor) field, and therefore casts a (tensor) vote. Each site collects all the votes cast at its location and encodes them into a new tensor. A local, parallel routine then simultaneously detects junctions, curves and region boundaries. The proposed approach is non-iterative, and the only free parameter is the size of the neighborhood, related to the scale. We illustrate the approach with results on a variety of images, then outline further applications.