Ph.D. Defense of Seong-Gyun Jeong

Curvilinear Structure Modeling and Its Applications in Computer Vision

Date: Monday, 23 November 2015
Time: 14:30
Place: Amphithéâtre Morgenstern, Bâtiment G. Kahn, INRIA Sophia Antipolis Méditerranée, 2004 route des Lucioles, 06902 Sophia Antipolis


Christine Graffigne, Université Paris Descartes, France
Tamás Szirányi , MTA SZTAKI & Budapest University of Technology and Economics, Hungary


Pascal Fua, EPFL, Switzerland
Xavier Descombes, Morpheme, INRIA Sophia Antipolis, France


Josiane Zerubia, Ayin, INRIA Sophia Antipolis, France
Yuliya Tarabalka, Titane, INRIA Sophia Antipolis, France


In this dissertation, we propose curvilinear structure reconstruction models based on stochastic modeling and ranking learning system. We assume that the entire line network can be decomposed into a set of line segments with variable lengths and orientations. This assumption enables us to reconstruct arbitrary shapes of curvilinear structure for different types of datasets. We compute curvilinear feature descriptors based on the image gradient profiles and the morphological profiles. For the stochastic model, we propose prior constraints that define the spatial interaction of line segments. To obtain an optimal configuration corresponding to the latent curvilinear structure, we combine multiple line hypotheses which are computed by MCMC sampling with different parameter sets. Moreover, we learn a ranking function which predicts the correspondence of the given line segment and the latent curvilinear structures. A novel graph-based method is proposed to infer the underlying curvilinear structure using the output rankings of the line segments. We apply our models to analyze curvilinear structure on static images. Experimental results on wide types of datasets demonstrate that the proposed curvilinear structure modeling outperforms the state-of-the-art techniques.

Curvilinear structure modeling, marked point process, structure inference, machine learning