2015
DOI: 10.1109/tcyb.2014.2375959
|View full text |Cite
|
Sign up to set email alerts
|

Online Signature Verification Based on DCT and Sparse Representation

Abstract: In this paper, a novel online signature verification technique based on discrete cosine transform (DCT) and sparse representation is proposed. We find a new property of DCT, which can be used to obtain a compact representation of an online signature using a fixed number of coefficients, leading to simple matching procedures and providing an effective alternative to deal with time series of different lengths. The property is also used to extract energy features. Furthermore, a new attempt to apply sparse repres… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
40
1

Year Published

2015
2015
2021
2021

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 101 publications
(41 citation statements)
references
References 40 publications
0
40
1
Order By: Relevance
“…EER of our model is lower than the EER of the state of the art models except the model proposed by Liu et al [25] . The results obtained demonstrated that the proposed model performs better than most of the functional as well as parametric models as given in Table 9.…”
Section: Comparative Studycontrasting
confidence: 63%
See 1 more Smart Citation
“…EER of our model is lower than the EER of the state of the art models except the model proposed by Liu et al [25] . The results obtained demonstrated that the proposed model performs better than most of the functional as well as parametric models as given in Table 9.…”
Section: Comparative Studycontrasting
confidence: 63%
“…A parametric based approach results in more compact representation as the entire signature is represented by means of a few parameters [25,36,38] .…”
Section: Introductionmentioning
confidence: 99%
“…The most common algorithms employed in time functionsbased systems are DTW (Dynamic Time Warping) [8], HMM (Hidden Markov Models) [9] [5], NN (Neural Networks) [10] and SVM (Support Vector Machines) [11]. DTW has the advantage that it does not need a previous training of the user models.…”
Section: Introductionmentioning
confidence: 99%
“…Signature verification techniques can be classified into two approaches: function-based and feature-based [20]. Function-based signature verification refers to the matching process using the original time-series data of a signature.…”
Section: Related Workmentioning
confidence: 99%