Interval valued symbolic representation of writer dependent features for online signature verification

Abstract

This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. Highlights  An approach for online signature verification based on writer dependent parameters  Interval valued symbolic representation of writer dependent features  Verification based on both symbolic representation and conventional representation  Lowest EER with symbolic representation and writer dependent parameters  Obtained results indicate the superiority of the proposed approach

A white-box analysis on the writer-independent dichotomy transformation applied to offline handwritten signature verification

“…Handwritten Signature Verification (HSV) systems are used to automatically recognize whether the signature provided by a writer belongs to the claimed person (Guru et al, 2017). In offline HSV, the signature is acquired after the writing process is completed, and the system deals with the signature as an image.…”

Automatic Signature Verification in the Mobile Cloud Scenario: Survey and Way Ahead

“…The use of a generic feature set over the entire population has demonstrated to be not effective, and many studies have been devoted to the selection of the most suitable features on a signer basis [33], [39], [70], [75], [105].…”

“…A pioneering work in this direction is the one by Vielhauer et al [99] where an interval matrix was used to obtain a hash vector from raw features. [99], [34], [33], [81] To some extent [53], [54], [104] Bio-Criptosystems Encryption schema where the kay is generated directly from the signature…”

“…Not Evaluated [20], [25], [52] In general, within this direction, any non-invertible transformation can be considered made up of several steps [53], [54], [104]. A Symbolic representation of signatures based on global features (in the form of interval-valued data) has been also proposed [34], as well as this approach could be also coupled with user-dependent feature selection [33]. Similarly, histograms able to describe raw features statistics can be considered [81].…”

Template Matching Using Time-Series Averaging and DTW With Dependent Warping for Online Signature Verification

“…In forensics, a signature has been generally examined by FDEs via consideration of its different characteristics in different writers with different writing conditions [13], [14]. In biometrics, better performance has been demonstrated through the use of writer-dependent features and threshold, as compared to the use of a common threshold [44], [45]. Thus, with its capacity to set an optimal threshold for each writer, the writer-dependent threshold is applied in this study.…”