Guide to Biometric Reference Systems and Performance Evaluation 2009
DOI: 10.1007/978-1-84800-292-0_6
|View full text |Cite
|
Sign up to set email alerts
|

Online Handwritten Signature Verification

Abstract: In this chapter, we first provide an overview of the existing main ap-6 proaches, databases, evaluation campaigns and the remaining challenges in online 7 handwritten signature verification. We then propose a new benchmarking frame-8 work for online signature verification by introducing the concepts of "Reference 9

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2011
2011
2021
2021

Publication Types

Select...
4
3
1

Relationship

1
7

Authors

Journals

citations
Cited by 12 publications
(7 citation statements)
references
References 26 publications
0
7
0
Order By: Relevance
“…It has been shown in different online signature competitions that pen coordinates are sufficient for obtaining good performance with DTW classifier [ 34 ]. Concerning the other classifier, we used 40 features [ 35 ] computed in a holistic manner on each signature sample. Indeed, it is well-known in the literature [ 36 ] that a global approach for signature matching requires a large amount of features for building a good enough classifier.…”
Section: Looking For the Menagerie By Output Scores’ Analysismentioning
confidence: 99%
“…It has been shown in different online signature competitions that pen coordinates are sufficient for obtaining good performance with DTW classifier [ 34 ]. Concerning the other classifier, we used 40 features [ 35 ] computed in a holistic manner on each signature sample. Indeed, it is well-known in the literature [ 36 ] that a global approach for signature matching requires a large amount of features for building a good enough classifier.…”
Section: Looking For the Menagerie By Output Scores’ Analysismentioning
confidence: 99%
“…These numbers of epochs proved to be enough for training with some reasonable margin for consistency. We have used only the publicly available SVC2004 dataset which has 40 signatures of 40 users, 1600 signatures in total unlike most of the other signature verification systems where they have used a much larger dataset like MYCT [20] or BioSecure Signature Subcorpus [20].…”
Section: Training and Testingmentioning
confidence: 99%
“…The signature corpus comprises genuine and shape-based highly skilled forgeries with natural dynamics [16,18]. In order to obtain the forgeries, each contributor is requested to imitate other signers by writing naturally.…”
Section: Handwritten Signatures Databasementioning
confidence: 99%
“…In order to obtain the forgeries, each contributor is requested to imitate other signers by writing naturally. For this task, they were given the printed signature to imitate and were asked not only to imitate the shape but also to generate the imitation without artifacts such as breaks or slow-downs (see [16,18] for more details of the acquisition procedure). Each signer contributes with 25 genuine signatures in five groups of five signatures each, and is forged 25 times by five different imitators.…”
Section: Handwritten Signatures Databasementioning
confidence: 99%