FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1551245400> ?p ?o ?g. }

• W1551245400 abstract "The principal objective of this thesis is to investigate approaches toward a robust automatic face authentication (AFA) system in weakly constrained environments. In this context, we develop new algorithms based on local features and generative models. In addition, particular attention is given to face localization which is a necessary step of a fully automatic system. In an authentication scenario, a person claims an identity and, using one or several face images to support this claim, the system classifies the person as either a true claimant (called client) or as an impostor. Unlike face identification, the face authentication task aims to assign a given face image into one of two classes. This task is particularly difficult since any person can be encountered; ie. the impostors have usually not been seen before. One of the other major challenges of AFA is the lack of reference images. Indeed, it is not realistic to have a huge amount of images for each identity. Usually, only one or a few images are available and they can not cover all the possible variabilities due to different expression, lighting, background, head pose, hair cut, etc. Generative models such as Gaussian mixture models (GMMs), one-dimensional hidden Markov models (1D-HMMs) and pseudo two-dimensional hidden Markov models (P2D-HMMs) have proved to be efficient for face identification. In this thesis, we propose to train generative models using maximum a posteriori (MAP) training instead of the traditionally used maximum likelihood (ML) criterion. We experimentally demonstrate the superiority of this approach over other training schemes. The main motivation for the use of MAP training is the ability of this algorithm to estimate robust model parameters when there is only a few training images available. Using P2D-HMM trained with MAP, we obtain better performance than state-of-the-art face authentication approaches. In a second part of this thesis, we proposed some improvements of the baseline systems in order to increase performances with minimal effects in computation time. The first proposition is to extend the feature vectors for the GMM approach in order to embed positional information. This new system improves slightly the performances comparing to the baseline GMM approach. The second proposed approach is an alternative 1D-HMM topology which allows the use of observation vectors representing image blocks instead a whole line for standard 1D-HMM implementation. The experiments demonstrate that this model is significantly more robust than the standard 1D-HMM. Due to is low complexity, it is also eight times faster than a P2D-HMM with the cost of a lower accuracy. Finally, in the last part of the thesis, we propose a new methodology to evaluate face localization algorithms in the context of face authentication. We first show the influence of localization errors on face authentication systems and then empirically demonstrate the problems of current localization performance measures when applied to this task. In order to properly evaluate the performance of a face localization algorithm, we then propose to embed the final application (the authentication system) into the performance measuring process. We show that our proposed method to evaluate localization algorithms better matches the final authentication performance." @default.
• W1551245400 created "2016-06-24" @default.
• W1551245400 creator A5056623642 @default.
• W1551245400 date "2005-01-01" @default.
• W1551245400 modified "2023-09-23" @default.
• W1551245400 title "Face Authentication Based on Local Features and Generative Models" @default.
• W1551245400 cites W108214665 @default.
• W1551245400 cites W1480865305 @default.
• W1551245400 cites W1482526072 @default.
• W1551245400 cites W1483135529 @default.
• W1551245400 cites W1484322501 @default.
• W1551245400 cites W1532520652 @default.
• W1551245400 cites W1538250395 @default.
• W1551245400 cites W1554663460 @default.
• W1551245400 cites W1579299427 @default.
• W1551245400 cites W1581809140 @default.
• W1551245400 cites W1583073584 @default.
• W1551245400 cites W1586405805 @default.
• W1551245400 cites W1596028639 @default.
• W1551245400 cites W1597803749 @default.
• W1551245400 cites W1604186087 @default.
• W1551245400 cites W1607048551 @default.
• W1551245400 cites W1620899341 @default.
• W1551245400 cites W1801124325 @default.
• W1551245400 cites W1852256319 @default.
• W1551245400 cites W1914482629 @default.
• W1551245400 cites W1982764588 @default.
• W1551245400 cites W2019915615 @default.
• W1551245400 cites W2033341974 @default.
• W1551245400 cites W2033419168 @default.
• W1551245400 cites W2041823554 @default.
• W1551245400 cites W2046399019 @default.
• W1551245400 cites W2049633694 @default.
• W1551245400 cites W2050802377 @default.
• W1551245400 cites W2060663686 @default.
• W1551245400 cites W2062195186 @default.
• W1551245400 cites W2067807322 @default.
• W1551245400 cites W2095757522 @default.
• W1551245400 cites W2097021277 @default.
• W1551245400 cites W2097277560 @default.
• W1551245400 cites W2101151916 @default.
• W1551245400 cites W2101294471 @default.
• W1551245400 cites W2105269526 @default.
• W1551245400 cites W2105628930 @default.
• W1551245400 cites W2106905947 @default.
• W1551245400 cites W2113624997 @default.
• W1551245400 cites W2116836390 @default.
• W1551245400 cites W2120420721 @default.
• W1551245400 cites W2120954940 @default.
• W1551245400 cites W2121551440 @default.
• W1551245400 cites W2121601095 @default.
• W1551245400 cites W2121647436 @default.
• W1551245400 cites W2123921160 @default.
• W1551245400 cites W2124925761 @default.
• W1551245400 cites W2125838338 @default.
• W1551245400 cites W2128716185 @default.
• W1551245400 cites W2133522721 @default.
• W1551245400 cites W2134262590 @default.
• W1551245400 cites W2136013692 @default.
• W1551245400 cites W2136440208 @default.
• W1551245400 cites W2138190382 @default.
• W1551245400 cites W2138243884 @default.
• W1551245400 cites W2138451337 @default.
• W1551245400 cites W2139085189 @default.
• W1551245400 cites W2140623795 @default.
• W1551245400 cites W2141393058 @default.
• W1551245400 cites W2143784448 @default.
• W1551245400 cites W2144143728 @default.
• W1551245400 cites W2144169730 @default.
• W1551245400 cites W2145073242 @default.
• W1551245400 cites W2146824864 @default.
• W1551245400 cites W2148603752 @default.
• W1551245400 cites W2150008717 @default.
• W1551245400 cites W2150591491 @default.
• W1551245400 cites W2150721269 @default.
• W1551245400 cites W2151129315 @default.
• W1551245400 cites W2151540856 @default.
• W1551245400 cites W2153281657 @default.
• W1551245400 cites W2158497138 @default.
• W1551245400 cites W2160367227 @default.
• W1551245400 cites W2164598857 @default.
• W1551245400 cites W2164847484 @default.
• W1551245400 cites W2166054752 @default.
• W1551245400 cites W2169078152 @default.
• W1551245400 cites W2169990695 @default.
• W1551245400 cites W2171692249 @default.
• W1551245400 cites W2217896605 @default.
• W1551245400 cites W2547514068 @default.
• W1551245400 cites W2799061466 @default.
• W1551245400 doi "https://doi.org/10.5075/epfl-thesis-3410" @default.
• W1551245400 hasPublicationYear "2005" @default.
• W1551245400 type Work @default.
• W1551245400 sameAs 1551245400 @default.
• W1551245400 citedByCount "2" @default.
• W1551245400 countsByYear W15512454002014 @default.
• W1551245400 crossrefType "journal-article" @default.
• W1551245400 hasAuthorship W1551245400A5056623642 @default.
• W1551245400 hasConcept C105795698 @default.
• W1551245400 hasConcept C116834253 @default.
• W1551245400 hasConcept C119857082 @default.

• next