2016
DOI: 10.1016/j.patcog.2016.02.007
|View full text |Cite
|
Sign up to set email alerts
|

Client threshold prediction in biometric signature recognition by means of Multiple Linear Regression and its use for score normalization

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
3
0

Year Published

2017
2017
2022
2022

Publication Types

Select...
3
3

Relationship

1
5

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 29 publications
0
3
0
Order By: Relevance
“…These results show that the score ratio proposal can be applied with small cohort sets and with small N values, which is very important for real applications. 2 The percentages have been calculated as follow:…”
Section: Results Analysismentioning
confidence: 99%
See 1 more Smart Citation
“…These results show that the score ratio proposal can be applied with small cohort sets and with small N values, which is very important for real applications. 2 The percentages have been calculated as follow:…”
Section: Results Analysismentioning
confidence: 99%
“…This work is focused on the Match stage. We have approached the Feature Extraction and Decision stages in previous works, [1] and [2] .…”
Section: Introductionmentioning
confidence: 99%
“…As a result of this observation, studies on the quality of biometric samples emerged in order to improve system performance and reliability. For instance, based on a quality measure, one could decide whether to: 1) alter the enrollment process including requesting users to re-enroll in the system, 2) adjust the decision threshold [39] or weighting function in a multimodal biometric system, 3) invoke different preprocessing or recognition algorithms [2], or 4) update the template [8]. A quality score could also be used as a deciding factor whether an additional biometric trait has to be required [28].…”
Section: Related Workmentioning
confidence: 99%
“…As a result, attackers could easily produce a signature that matches the template, resulting in a compromised account. In this context, an assessment of biometric template characteristics could be used to design proper mechanisms to cope with such weak templates [2,13,28,39]. For example, given a template that is predicted to yield high FAR (False Acceptance Rate: the likelihood that forgery samples will be incorrectly accepted by the system) but low FRR (False Rejection Rate: the likelihood that genuine samples will be incorrectly rejected by the system), the system could examine whether a few bad enrolled samples could be safely removed to lower FAR without degrading FRR.…”
Section: Introductionmentioning
confidence: 99%
“…The ensemble group did not demand normalization of the dataset, once that normalization is a preprocessing step that uses tree-based approach, like RF and ADAB, do not require, even so, other MLs based on matrix distance as the regularizations and MLR are necessary(VIVARACHO-PASCUAL et al 2016). …”
mentioning
confidence: 99%