Zobrazit minimální záznam



dc.contributor.advisorFranc, Vojtěch
dc.contributor.authorUřičář, Michal
dc.date.accessioned2017-06-09T11:14:08Z
dc.date.available2017-06-09T11:14:08Z
dc.date.issued2017
dc.identifier.urihttp://hdl.handle.net/10467/70545
dc.description.abstractIn this thesis, we tackle the problem of designing a multi-view facial landmark detector which is robust and works in real-time on low-end hardware. Our landmark detector is an instance of the structured output classi ers describing the face by a mixture of tree based Deformable Part Models (DPM). We propose to learn parameters of the detector by the Structured Output Support Vector Machine algorithm which, in contrast to existing methods, directly optimizes a loss function closely related to the standard evaluation metrics used in landmark detection. We also propose a novel two-stage approach to learn the multi-view landmark detectors, which provides better localization accuracy and signi cantly reduces the overall learning time. We propose several speedups that enable to use the globally optimal prediction strategy based on the dynamic programming in real time even for dense landmark sets. The empirical evaluation shows that the proposed detector is competitive with the current state-ofthe- art both regarding the accuracy and speed. We also propose two improvements of the Bundle Method for Regularized Risk Minimization (BMRM) algorithm which is among the most popular batch solvers used in structured output learning. First, we propose to augment the objective function by a quadratic prox-center whose strength is controlled by a novel adaptive strategy preventing zig-zag behavior in the cases when the genuine regularization term is weak. Second, we propose to speed up convergence by using multiple cutting plane models which better approximate the objective function with minimal increase in the computational cost. Experimental evaluation shows that the new BMRM algorithm which uses both improvements speeds up learning up to an order of magnitude on standard computer vision benchmarks, and 3 to 4 times when applied to the learning of the DPM based landmark detector. ven
dc.language.isoenen
dc.titleMulti-view Facial Landmark Detectionen
dc.typedisertační prácecze
dc.description.departmentKatedra kybernetiky
theses.degree.disciplineUmělá inteligence a biokybernetika
theses.degree.grantorČeské vysoké učení technické v Praze. Fakulta elektrotechnická. Katedra kybernetiky
theses.degree.programmeElektrotechnika a informatika


Soubory tohoto záznamu



Tento záznam se objevuje v následujících kolekcích

Zobrazit minimální záznam