Segmentation by transduction

Olivier Duchenne (1) , Jean-Yves Audibert (1, 2, 3) , Renaud Keriven (2, 3) , Jean Ponce (1) , Florent Ségonne (2, 3)

1 WILLOW - Models of visual object recognition and scene understanding
2 CERTIS - Centre d'Enseignement et de Recherche en Technologies de l'Information et Systèmes
3 LIGM - Laboratoire d'Informatique Gaspard-Monge

This paper addresses the problem of segmenting an image into regions consistent with user-supplied seeds (e.g., a sparse set of broad brush strokes). We view this task as a statistical transductive inference, in which some pixels are already associated with given zones and the remaining ones need to be classified. Our method relies on the Laplacian graph regularizer, a powerful manifold learning tool that is based on the estimation of variants of the Laplace-Beltrami operator and is tightly related to diffusion processes. Segmentation is modeled as the task of finding matting coefficients for unclassified pixels given known matting coefficients for seed pixels. The proposed algorithm essentially relies on a high margin assumption in the space of pixel characteristics. It is simple, fast, and accurate, as demonstrated by qualitative results on natural images and a quantitative comparison with state-of-the-art methods on the Microsoft GrabCut segmentation database.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Olivier Duchenne, Jean-Yves Audibert, Renaud Keriven, Jean Ponce, Florent Ségonne. Segmentation by transduction. CVPR 2008 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2008, Anchorage, United States. pp.1-8, ⟨10.1109/CVPR.2008.4587419⟩. ⟨hal-00834989⟩