On the Beneficial Effect of Noise in Vertex Localization

Konstantinos Raftopoulos (1, 2) , Stefanos Kollias (3) , Dionysios Sourlas (4) , Marin Ferecatu (2)

1 IVML - Image, Video and Multimedia Laboratory
2 CEDRIC - VERTIGO - CEDRIC. Données complexes, apprentissage et représentations
3 University of Lincoln
4 Unilever R&D

A theoretical and experimental analysis related to the effect of noise in the task of vertex identification in unknown shapes is presented. Shapes are seen as real functions of their closed boundary. An alternative global perspective of curvature is examined providing insight into the process of noise-enabled vertex localization. The analysis reveals that noise facilitates in the localization of certain vertices. The concept of noising is thus considered and a relevant global method for localizing Global Vertices is investigated in relation to local methods under the presence of increasing noise. Theoretical analysis reveals that induced noise can indeed help localizing certain vertices if combined with global descriptors. Experiments with noise and a comparison to localized methods validate the theoretical results.

Domains: Computer Vision and Pattern Recognition [cs.CV]; Image Processing [eess.IV]

Konstantinos Raftopoulos, Stefanos Kollias, Dionysios Sourlas, Marin Ferecatu. On the Beneficial Effect of Noise in Vertex Localization. International Journal of Computer Vision, 2018, 126 (1), pp.111-139. ⟨10.1007/s11263-017-1034-6⟩. ⟨hal-02469070⟩