2011 International Conference on Process Automation, Control and Computing 2011
DOI: 10.1109/pacc.2011.5979022
|View full text |Cite
|
Sign up to set email alerts
|

Improved Partial Fingerprint Matching Based on Score Level Fusion Using Pore and SIFT Features

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
14
0

Year Published

2012
2012
2022
2022

Publication Types

Select...
6
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 19 publications
(14 citation statements)
references
References 9 publications
0
14
0
Order By: Relevance
“…Second, we assume that it is not practical to cover an entire touchscreen with transparent fingerprint sensors, due to the cost, performance, and efficiency issues. Third, existing fingerprint match techniques, such as these described in [12], are robust enough to be applied to partial fingerprints. And finally, fingerprint biometric is used not only for unlocking a local mobile device but also for continuously authenticating the user after the one-shot the login process.…”
Section: A Local Identity Security Mechanismmentioning
confidence: 99%
“…Second, we assume that it is not practical to cover an entire touchscreen with transparent fingerprint sensors, due to the cost, performance, and efficiency issues. Third, existing fingerprint match techniques, such as these described in [12], are robust enough to be applied to partial fingerprints. And finally, fingerprint biometric is used not only for unlocking a local mobile device but also for continuously authenticating the user after the one-shot the login process.…”
Section: A Local Identity Security Mechanismmentioning
confidence: 99%
“…The partial fingerprint matching extracted the pore feature and SIFT feature points. The score level fusion was applied after matching score was calculated [25]. Face and finger print modalities were fused under score level by modeling the causal relationships by Bayesian Networks [26].…”
Section: Ii) Fusion At Matching Score Levelmentioning
confidence: 99%
“…It has excellent performance in solving rotation, scaling or radiation transformation problems of images matching [5]. SIFT algorithm has good characteristics in partial feature extraction of feature-points [6] and is widely used in remote sensing image matching [7], biological feature recognition [8], and so on. But it also has some drawbacks such as too many feature points, too large dimension of the descriptor and too high time consuming of computation in matching process.…”
Section: Introductionmentioning
confidence: 99%