Abstract
The idea of user-specific multimodal biometrics is pioneered by [1] and further exploited by [2] recently. In this paper, we look into several issues pertaining to user-specific multimodal biometric verification. These issues include the small sample size problem, learning of local decision hyperplanes and setting of local thresholds. For small sample size problem, the noise-injection technique and a feature scaling-space technique are considered. For local learning, we adopt a recently proposed reduced polynomial since it has fast single-step computation and accurate estimation. For setting of local decision thresholds, nine baselines are identified. Extensive experiments are performed on a moderate data set and relatively conclusive results are observed.
| Original language | English |
|---|---|
| Title of host publication | 2004 8th International Conference on Control, Automation, Robotics and Vision (ICARCV) |
| Pages | 1268-1273 |
| Number of pages | 6 |
| Volume | 2 |
| Publication status | Published - 2004 Dec 1 |
| Event | 8th International Conference on Control, Automation, Robotics and Vision (ICARCV) - Kunming, China Duration: 2004 Dec 6 → 2004 Dec 9 |
Other
| Other | 8th International Conference on Control, Automation, Robotics and Vision (ICARCV) |
|---|---|
| Country | China |
| City | Kunming |
| Period | 04/12/6 → 04/12/9 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Engineering(all)
Cite this
}
Some learning issues in user-specific multimodal biometrics. / Toh, Kar Ann; Yau, Wei Yun.
2004 8th International Conference on Control, Automation, Robotics and Vision (ICARCV). Vol. 2 2004. p. 1268-1273 TuM4.06 - P1868.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Some learning issues in user-specific multimodal biometrics
AU - Toh, Kar Ann
AU - Yau, Wei Yun
PY - 2004/12/1
Y1 - 2004/12/1
N2 - The idea of user-specific multimodal biometrics is pioneered by [1] and further exploited by [2] recently. In this paper, we look into several issues pertaining to user-specific multimodal biometric verification. These issues include the small sample size problem, learning of local decision hyperplanes and setting of local thresholds. For small sample size problem, the noise-injection technique and a feature scaling-space technique are considered. For local learning, we adopt a recently proposed reduced polynomial since it has fast single-step computation and accurate estimation. For setting of local decision thresholds, nine baselines are identified. Extensive experiments are performed on a moderate data set and relatively conclusive results are observed.
AB - The idea of user-specific multimodal biometrics is pioneered by [1] and further exploited by [2] recently. In this paper, we look into several issues pertaining to user-specific multimodal biometric verification. These issues include the small sample size problem, learning of local decision hyperplanes and setting of local thresholds. For small sample size problem, the noise-injection technique and a feature scaling-space technique are considered. For local learning, we adopt a recently proposed reduced polynomial since it has fast single-step computation and accurate estimation. For setting of local decision thresholds, nine baselines are identified. Extensive experiments are performed on a moderate data set and relatively conclusive results are observed.
UR - http://www.scopus.com/inward/record.url?scp=21244483559&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=21244483559&partnerID=8YFLogxK
M3 - Conference contribution
SN - 0780386531
SN - 9780780386532
VL - 2
SP - 1268
EP - 1273
BT - 2004 8th International Conference on Control, Automation, Robotics and Vision (ICARCV)
ER -