Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133732147> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W3133732147 abstract "The thesis presents a 2D face recognition system using Markov random field matching methodology for establishing dense correspondences between a pair of images in the presence of pose changes and self-occlusion. The proposed method, which exploits both shape and texture differences between images, achieves very competitive performance compared to the current approaches. The algorithm bypasses the need for geometric pre-processing of face images. By virtue of the matching methodology embedded in the algorithm, the proposed approach can cope with moderate translation, in and out of plane rotation, scaling and perspective effects. Also by employing a graphical model based approach, the proposed system circumvents the need for non-frontal images being available for training a pose-invariant face recognition system. In contrast to the state-of-the-art approaches based on 3D models, the approach operates on 2D images and bypasses the need for 3D face training data and avoids the vagaries of 3D face model to 2D face image fitting. From the point of view of object recognition based on graphical models, the matching energy in graph based approaches is shown to exhibit certain drawbacks and should not be used as a similarity criterion for the hypothesis selection directly. The main shortcomings of the energy functional (using at most pairwise potentials) are identified and a plausible energy normalization scheme is proposed. In order to reduce the computational burden of the inference in the model, two multi-scale processing approaches are proposed. One employs the super-coupling transform in order to solve the matching problem in a multiresolution fashion. The other is heuristic but surprisingly leads to good results. Last but not least, a sparse graphical model for facial feature localization is proposed. The method takes advantage of the sparsity of facial image features in order to speed-up the matching process. The conditional dependencies between different groups of image primitives are included as higher order interactions based on point distribution models and linearity-based priors. The sparse model has been successfully applied to the task of facial feature localization and also as an initialization step to speed-up inference in a more costly matching approach." @default.
- W3133732147 created "2021-03-15" @default.
- W3133732147 creator A5091897876 @default.
- W3133732147 date "2010-01-01" @default.
- W3133732147 modified "2023-09-26" @default.
- W3133732147 title "Pose-Invariant 2D Face Recognition by Matching Using Graphical Models." @default.
- W3133732147 hasPublicationYear "2010" @default.
- W3133732147 type Work @default.
- W3133732147 sameAs 3133732147 @default.
- W3133732147 citedByCount "0" @default.
- W3133732147 crossrefType "dissertation" @default.
- W3133732147 hasAuthorship W3133732147A5091897876 @default.
- W3133732147 hasConcept C136886441 @default.
- W3133732147 hasConcept C144024400 @default.
- W3133732147 hasConcept C153180895 @default.
- W3133732147 hasConcept C154945302 @default.
- W3133732147 hasConcept C155846161 @default.
- W3133732147 hasConcept C190470478 @default.
- W3133732147 hasConcept C19165224 @default.
- W3133732147 hasConcept C31510193 @default.
- W3133732147 hasConcept C31972630 @default.
- W3133732147 hasConcept C33923547 @default.
- W3133732147 hasConcept C37914503 @default.
- W3133732147 hasConcept C41008148 @default.
- W3133732147 hasConcept C52622490 @default.
- W3133732147 hasConcept C64876066 @default.
- W3133732147 hasConceptScore W3133732147C136886441 @default.
- W3133732147 hasConceptScore W3133732147C144024400 @default.
- W3133732147 hasConceptScore W3133732147C153180895 @default.
- W3133732147 hasConceptScore W3133732147C154945302 @default.
- W3133732147 hasConceptScore W3133732147C155846161 @default.
- W3133732147 hasConceptScore W3133732147C190470478 @default.
- W3133732147 hasConceptScore W3133732147C19165224 @default.
- W3133732147 hasConceptScore W3133732147C31510193 @default.
- W3133732147 hasConceptScore W3133732147C31972630 @default.
- W3133732147 hasConceptScore W3133732147C33923547 @default.
- W3133732147 hasConceptScore W3133732147C37914503 @default.
- W3133732147 hasConceptScore W3133732147C41008148 @default.
- W3133732147 hasConceptScore W3133732147C52622490 @default.
- W3133732147 hasConceptScore W3133732147C64876066 @default.
- W3133732147 hasLocation W31337321471 @default.
- W3133732147 hasOpenAccess W3133732147 @default.
- W3133732147 hasPrimaryLocation W31337321471 @default.
- W3133732147 hasRelatedWork W1506635893 @default.
- W3133732147 hasRelatedWork W1563183066 @default.
- W3133732147 hasRelatedWork W1601263219 @default.
- W3133732147 hasRelatedWork W1975833668 @default.
- W3133732147 hasRelatedWork W1981330189 @default.
- W3133732147 hasRelatedWork W2025842678 @default.
- W3133732147 hasRelatedWork W2075798104 @default.
- W3133732147 hasRelatedWork W2146955525 @default.
- W3133732147 hasRelatedWork W2295060673 @default.
- W3133732147 hasRelatedWork W2335698258 @default.
- W3133732147 hasRelatedWork W2617152883 @default.
- W3133732147 hasRelatedWork W2737897248 @default.
- W3133732147 hasRelatedWork W2775161256 @default.
- W3133732147 hasRelatedWork W2911502624 @default.
- W3133732147 hasRelatedWork W2989919481 @default.
- W3133732147 hasRelatedWork W3003704657 @default.
- W3133732147 hasRelatedWork W3035174858 @default.
- W3133732147 hasRelatedWork W3154745432 @default.
- W3133732147 hasRelatedWork W3193597575 @default.
- W3133732147 hasRelatedWork W3211311155 @default.
- W3133732147 isParatext "false" @default.
- W3133732147 isRetracted "false" @default.
- W3133732147 magId "3133732147" @default.
- W3133732147 workType "dissertation" @default.