Title :
Face recognition at-a-distance using texture, Sparse-Stereo, and Dense-Stereo
Author :
Abdelrahman, Mostafa ; Elhabian, Shireen ; Ali, Asem ; Farag, Aly A.
Author_Institution :
Comput. Vision & Image Process. Lab., Univ. of Louisville, Louisville, KY, USA
Abstract :
This paper proposes a framework for face recognition at a distance based on texture, Sparse-Stereo, and Dense-stereo reconstruction. We develop a 3D acquisition system that consists of two CCD stereo cameras mounted on pan-tilt units with adjustable baseline. In this paper we introduce our stereo-based indoor/outdoor environment and different ranges human faces database. Also, we propose a front-to-end system of 3D face reconstruction and recognition. We first detect the facial region and extract its landmark points, which are used to initialize the face alignment algorithm. The fitted mesh vertices, generated from the face alignment process, provide point correspondences between the left and right images of a stereo pair; stereo-based reconstruction is then used to infer the 3D information of the mesh vertices. Also the dense 3D is reconstructed for the cropped stereo pair based on graph cut approach. We perform experiments regarding the use of different features extracted from these vertices for face recognition. The cumulative rank curves (CMC), which are generated using the proposed framework, confirm the feasibility of the proposed work for long distance recognition of human faces.
Keywords :
CCD image sensors; face recognition; feature extraction; graph theory; image reconstruction; image texture; stereo image processing; visual databases; 3D acquisition system; 3D face reconstruction; CCD stereo cameras; cropped stereo pair; cumulative rank curves; dense-stereo; face alignment algorithm; face recognition at a distance; feature extraction; front-to-end system; graph cut approach; human faces database; image texture; long distance recognition; mesh vertices; pan-tilt units; sparse stereo; stereo-based indoor-outdoor environment; Databases; Face; Face recognition; Feature extraction; Image color analysis; Skin; Three dimensional displays; 3D reconstruction; Face recognition; Sparse; Stereo; skin modeling;
Conference_Titel :
Multimedia Technology (ICMT), 2011 International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-61284-771-9
DOI :
10.1109/ICMT.2011.6001979