In this work, we propose and experiment an original solution to 3D face recognition that supports accurate face matching also in cases where just some parts of probe scans are available. In the proposed approach, distinguishing traits of the face are captured by first extracting keypoints of the 3D depth image and then measuring how the face depth changes along facial sections between pairs of keypoints. Face similarity is evaluated by comparing facial sections across inlier pairs of keypoints that match between probe and gallery scans. In doing so, facial sections of the gallery scans are associated with a saliency measure in order to distinguish sections that model characterizing traits of some subjects from sections that are frequently observed in the face of many different subjects. The recognition accuracy of the approach is experimented using the Face Recognition Grand Challenge v2.0 dataset.
Facial Surface Sections for Recognition of 3D Faces with Missing Parts / S. Berretti; A. Del Bimbo; P. Pala. - STAMPA. - 2:(2011), pp. 257-262. (Intervento presentato al convegno Traitement at Analyse de l'Information Méthodes et Applications, TAIMA 2011, Session Spéciale Reconnaissance Faciale 3D/4D et Biométrie tenutosi a Hammamet, Tunisia nel Ottobre 2011).
Facial Surface Sections for Recognition of 3D Faces with Missing Parts
BERRETTI, STEFANO;DEL BIMBO, ALBERTO;PALA, PIETRO
2011
Abstract
In this work, we propose and experiment an original solution to 3D face recognition that supports accurate face matching also in cases where just some parts of probe scans are available. In the proposed approach, distinguishing traits of the face are captured by first extracting keypoints of the 3D depth image and then measuring how the face depth changes along facial sections between pairs of keypoints. Face similarity is evaluated by comparing facial sections across inlier pairs of keypoints that match between probe and gallery scans. In doing so, facial sections of the gallery scans are associated with a saliency measure in order to distinguish sections that model characterizing traits of some subjects from sections that are frequently observed in the face of many different subjects. The recognition accuracy of the approach is experimented using the Face Recognition Grand Challenge v2.0 dataset.File | Dimensione | Formato | |
---|---|---|---|
taima11_final.pdf
Accesso chiuso
Descrizione: documento finale
Tipologia:
Versione finale referata (Postprint, Accepted manuscript)
Licenza:
Tutti i diritti riservati
Dimensione
453.61 kB
Formato
Adobe PDF
|
453.61 kB | Adobe PDF | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.