TY - GEN
T1 - A projection framework for biometric scores fusion
AU - Toh, Kar Ann
PY - 2010
Y1 - 2010
N2 - This paper presents a projection framework for biometric scores fusion. Essentially, the framework consists of a projection stage and a learning stage. Apart from investigating into several relatively new projection models for biometric fusion, the projection stage attempts to unify these models into a single parametric structure. Three learning methods are investigated in conjunction with six projection models for their impacts on verification accuracy expressed in terms of equal error rate. An extensive experiment of these model and learning combinations on 32 fusion data sets are performed in the evaluation.
AB - This paper presents a projection framework for biometric scores fusion. Essentially, the framework consists of a projection stage and a learning stage. Apart from investigating into several relatively new projection models for biometric fusion, the projection stage attempts to unify these models into a single parametric structure. Three learning methods are investigated in conjunction with six projection models for their impacts on verification accuracy expressed in terms of equal error rate. An extensive experiment of these model and learning combinations on 32 fusion data sets are performed in the evaluation.
UR - http://www.scopus.com/inward/record.url?scp=79952404915&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79952404915&partnerID=8YFLogxK
U2 - 10.1109/ICARCV.2010.5707787
DO - 10.1109/ICARCV.2010.5707787
M3 - Conference contribution
AN - SCOPUS:79952404915
SN - 9781424478132
T3 - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
SP - 1262
EP - 1267
BT - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
T2 - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
Y2 - 7 December 2010 through 10 December 2010
ER -