|
|
Biometric Recognition of 3D Faces
Mráček, Štěpán ; Drahanský, Martin (oponent) ; Dvořák, Radim (vedoucí práce)
This Master's Thesis was performed during a study stay at the Gjovik University College, Norway. This Thesis is about biometric 3D face recognition. A general biometric system as well as specific techniques used in 2D and 3D face recognition are described. An automatic modular 3D face recognition method will be proposed. The algorithm is developed, tested and evaluated on the Face Recognition Grand Challenge (FRGC) database. During the preprocessing part, facial landmarks are located on the face surface and the three dimensional model is aligned to a predefined position. In the comparison module, the input probe scan is compared to the gallery template. There are three fundamental face recognition algorithms employed during the recognition pipeline -- the eigenface method (PCA), the recognition using histogram-based features, and the recognition based on the anatomical-Bertillon features of the face. Finally the decision module fuses the scores provided by the utilized recognition techniques. The resulting performance is better than any of utilized recognition algorithms.
|
|
|
Multikamerová biometrická brána pro identifikaci osob
Kosík, Dominik ; Orság, Filip (oponent) ; Goldmann, Tomáš (vedoucí práce)
Tato práce řeší vytvoření biometrické brány pro identifikaci osob. Identifikace probíhá za pomocí 5 barevných kamer a IR kamery. IR kamera zajišťuje detekci osoby a následně se ze snímku barevných kamer vytváří 3D model obličeje osoby. Na základě tohoto modelu se provádí identifikace. Jelikož při vytváření samotného 3D modelu docházelo k nepřesnostem, což má vliv na rozpoznání osoby, není výsledná identifikace dostatečně přesná. Z toho důvodu je zapotřebí upravit algoritmy zpracovávající 3D model, a tak dosáhnout dostatečné přesnosti.
|
|
|
Hybrid 3D Face Recognition
Mráček, Štěpán ; Bours, Patrick (oponent) ; Bronstein, Michael (oponent) ; Drahanský, Martin (vedoucí práce)
This Ph.D. thesis deals with the biometric recognition of 3D faces. Contemporary recognition methods and techniques are presented first. After that, the new recognition algorithm is proposed. It is based on the multialgorithmic fusion. The input 3D face scan is processed by the individual recognition units and the final decision about the subject identity is the result of combination of involved recognition unit outputs. Proposed approach has been tested on the publicly available FRGC v 2.0 database as well as on our own databases acquired with the Microsoft Kinect and SoftKinetic DS325 sensors.
|
|
|
Multikamerová biometrická brána pro identifikaci osob
Kosík, Dominik ; Orság, Filip (oponent) ; Goldmann, Tomáš (vedoucí práce)
Tato práce řeší vytvoření biometrické brány pro identifikaci osob. Identifikace probíhá za pomocí 5 barevných kamer a IR kamery. IR kamera zajišťuje detekci osoby a následně se ze snímku barevných kamer vytváří 3D model obličeje osoby. Na základě tohoto modelu se provádí identifikace. Jelikož při vytváření samotného 3D modelu docházelo k nepřesnostem, což má vliv na rozpoznání osoby, není výsledná identifikace dostatečně přesná. Z toho důvodu je zapotřebí upravit algoritmy zpracovávající 3D model, a tak dosáhnout dostatečné přesnosti.
|
|
|
Hybrid 3D Face Recognition
Mráček, Štěpán ; Bours, Patrick (oponent) ; Bronstein, Michael (oponent) ; Drahanský, Martin (vedoucí práce)
This Ph.D. thesis deals with the biometric recognition of 3D faces. Contemporary recognition methods and techniques are presented first. After that, the new recognition algorithm is proposed. It is based on the multialgorithmic fusion. The input 3D face scan is processed by the individual recognition units and the final decision about the subject identity is the result of combination of involved recognition unit outputs. Proposed approach has been tested on the publicly available FRGC v 2.0 database as well as on our own databases acquired with the Microsoft Kinect and SoftKinetic DS325 sensors.
|
|
|
Biometric Recognition of 3D Faces
Mráček, Štěpán ; Drahanský, Martin (oponent) ; Dvořák, Radim (vedoucí práce)
This Master's Thesis was performed during a study stay at the Gjovik University College, Norway. This Thesis is about biometric 3D face recognition. A general biometric system as well as specific techniques used in 2D and 3D face recognition are described. An automatic modular 3D face recognition method will be proposed. The algorithm is developed, tested and evaluated on the Face Recognition Grand Challenge (FRGC) database. During the preprocessing part, facial landmarks are located on the face surface and the three dimensional model is aligned to a predefined position. In the comparison module, the input probe scan is compared to the gallery template. There are three fundamental face recognition algorithms employed during the recognition pipeline -- the eigenface method (PCA), the recognition using histogram-based features, and the recognition based on the anatomical-Bertillon features of the face. Finally the decision module fuses the scores provided by the utilized recognition techniques. The resulting performance is better than any of utilized recognition algorithms.
|
host ::
RSS.