Abstract
In this paper, we address the multimodal biometric decision fusion problem. By exploring into the user-specific approach for learning and threshold setting, four possible paradigms for learning and decision making are investigated. Since each user requires a decision hyperplane specific to him in order to achieve good verification accuracy, those tedious iterative training methods like the neural network approach would not be suitable. We propose to use a model that requires only a single training step for this application. The four global and local learning and decision paradigms are then explored to observe their decision capability. Besides the proposal of a relevant receiver operating characteristic performance for the local decision, extensive experiments were conducted to observe the verification performance for fusion of two and three biometrics.
| Original language | English |
|---|---|
| Pages (from-to) | 3059-3072 |
| Number of pages | 14 |
| Journal | IEEE Transactions on Signal Processing |
| Volume | 52 |
| Issue number | 10 |
| DOIs | |
| Publication status | Published - 2004 Oct 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Signal Processing
- Electrical and Electronic Engineering
Cite this
}
Exploiting global and local decisions for multimodal biometrics verification. / Toh, Kar Ann; Jiang, Xudong; Yau, Wei Yun.
In: IEEE Transactions on Signal Processing, Vol. 52, No. 10, 01.10.2004, p. 3059-3072.Research output: Contribution to journal › Article
TY - JOUR
T1 - Exploiting global and local decisions for multimodal biometrics verification
AU - Toh, Kar Ann
AU - Jiang, Xudong
AU - Yau, Wei Yun
PY - 2004/10/1
Y1 - 2004/10/1
N2 - In this paper, we address the multimodal biometric decision fusion problem. By exploring into the user-specific approach for learning and threshold setting, four possible paradigms for learning and decision making are investigated. Since each user requires a decision hyperplane specific to him in order to achieve good verification accuracy, those tedious iterative training methods like the neural network approach would not be suitable. We propose to use a model that requires only a single training step for this application. The four global and local learning and decision paradigms are then explored to observe their decision capability. Besides the proposal of a relevant receiver operating characteristic performance for the local decision, extensive experiments were conducted to observe the verification performance for fusion of two and three biometrics.
AB - In this paper, we address the multimodal biometric decision fusion problem. By exploring into the user-specific approach for learning and threshold setting, four possible paradigms for learning and decision making are investigated. Since each user requires a decision hyperplane specific to him in order to achieve good verification accuracy, those tedious iterative training methods like the neural network approach would not be suitable. We propose to use a model that requires only a single training step for this application. The four global and local learning and decision paradigms are then explored to observe their decision capability. Besides the proposal of a relevant receiver operating characteristic performance for the local decision, extensive experiments were conducted to observe the verification performance for fusion of two and three biometrics.
UR - http://www.scopus.com/inward/record.url?scp=4744361171&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=4744361171&partnerID=8YFLogxK
U2 - 10.1109/TSP.2004.833862
DO - 10.1109/TSP.2004.833862
M3 - Article
VL - 52
SP - 3059
EP - 3072
JO - IEEE Transactions on Signal Processing
JF - IEEE Transactions on Signal Processing
SN - 1053-587X
IS - 10
ER -