Title :
Mixing fingerprints for generating virtual identities
Author :
Othman, Asem ; Ross, Arun
Author_Institution :
Lane Dept. of Comput. Sci. & Electr. Eng., West Virginia Univ., Morgantown, WV, USA
fDate :
Nov. 29 2011-Dec. 2 2011
Abstract :
This work explores the possibility of mixing two different fingerprints at the image level in order to generate a new fingerprint. To mix two fingerprints, each fingerprint is decomposed into two different components, viz., the continuous and spiral components. After pre-aligning the components of each fingerprint, the continuous component of one fingerprint is combined with the spiral component of the other fingerprint image. Experiments on a subset of the WVU fingerprint dataset show that the proposed approach can be used to generate virtual identities from images of two different fingers pertaining to a single individual or different individuals.
Keywords :
fingerprint identification; image fusion; set theory; virtual reality; WVU fingerprint dataset; continuous component; fingerprint image; fingerprint mixing; image level; spiral component; virtual identity; Fingerprint recognition;
Conference_Titel :
Information Forensics and Security (WIFS), 2011 IEEE International Workshop on
Conference_Location :
Iguacu Falls
Print_ISBN :
978-1-4577-1017-9
Electronic_ISBN :
978-1-4577-1018-6
DOI :
10.1109/WIFS.2011.6123152