Université du Luxembourg
Deformation Based Curved Shape Representation.
Degree: 2017, Université du Luxembourg
Representation and modelling of an objects' shape is critical in object recognition, synthesis, tracking and many other applications in computer vision. As a result, there is a wide range of approaches in formulating representation space and quantifying the notion of similarity between shapes. A similarity metric between shapes is a basic building block in modelling shape categories, optimizing shape valued functionals, and designing a classifier. Consequently, any subsequent shape based computation is fundamentally dependent on the computational efficiency, robustness, and invariance to shape preserving transformations of the defined similarity metric.
In this thesis, we propose a novel finite dimensional shape representation framework that leads to a computationally efficient, closed form solution, and noise tolerant similarity distance function. Several important characteristics of the proposed curved shape representation approach are discussed in relation to earlier works. Subsequently, two different solutions are proposed for optimal parameter estimation of curved shapes. Hence, providing two possible solutions for the point correspondence estimation problem between two curved shapes. Later in the thesis, we show that several statistical models can readily be adapted to the proposed shape representation framework for object category modelling. The thesis finalizes by exploring potential applications of the proposed curved shape representation in 3D facial surface and facial expression representation and modelling.
Advisors/Committee Members: Ottersten, Björn [superviser], Sabetzadeh, Mehrdad [president of the jury], Fofi, David [secretary], Aouada, Djamila [member of the jury], Berretti, Stefano [member of the jury], University of Luexmbourg: Security, Reliablity and Trust(SnT) [research center].
Subjects/Keywords: Computer vision; Modelling; Deformation; Optimization; Engineering, computing & technology :: Computer science [C05]; Ingénierie, informatique & technologie :: Sciences informatiques [C05]
to Zotero / EndNote / Reference
APA (6th Edition):
Demisse, G. (2017). Deformation Based Curved Shape Representation. (Doctoral Dissertation). Université du Luxembourg. Retrieved from http://orbilu.uni.lu/handle/10993/33029
Chicago Manual of Style (16th Edition):
Demisse, Girum. “Deformation Based Curved Shape Representation.” 2017. Doctoral Dissertation, Université du Luxembourg. Accessed October 15, 2019.
MLA Handbook (7th Edition):
Demisse, Girum. “Deformation Based Curved Shape Representation.” 2017. Web. 15 Oct 2019.
Demisse G. Deformation Based Curved Shape Representation. [Internet] [Doctoral dissertation]. Université du Luxembourg; 2017. [cited 2019 Oct 15].
Available from: http://orbilu.uni.lu/handle/10993/33029.
Council of Science Editors:
Demisse G. Deformation Based Curved Shape Representation. [Doctoral Dissertation]. Université du Luxembourg; 2017. Available from: http://orbilu.uni.lu/handle/10993/33029