Multiple Generation of Bengali Static Signatures

Abstract

Handwritten signature datasets are really necessary for the purpose of developing and training automatic signature verification systems. It is desired that all samples in a signature dataset should exhibit both inter-personal and intra-personal variability. A possibility to model this reality seems to be obtained through the synthesis of signatures. In this paper we propose a method based on motor equivalence model theory to generate static Bengali signatures. This theory divides the human action to write mainly into cognitive and motor levels. Due to difference between scripts, we have redesigned our previous synthesizer [1],[2], which generates static Western signatures. The experiments assess whether this method can approach the intra and interpersonal variability of the Bengali-100 Static Signature DB from a performance-based validation. The similarities reported in the experimental results proof the ability of the synthesizer to generate signature images in this script.

A Perspective Analysis of Handwritten Signature Technology

“…The static version is eventually generated by applying an ink deposition model. A similar proposal for generating offline Bengali and Devanagari signatures is reported in [47,74].…”

Intrapersonal Parameter Optimization for Offline Handwritten Signature Augmentation

“…Signature duplication methods consist of algorithms used to generate new artificial signatures, with one or more signatures used as seeds [18]. Duplication methods can be divided into: i) the creation of online (dynamic) signatures using real online samples [17], [22], [32]- [38]; ii) the creation of offline (static) signatures using real online samples [20], [24], [39]- [42]; iii) the creation of offline signatures using real offline samples [18], [19], [21], [23], [43]- [47]; and iv) the creation of online signatures by using real offline samples. Despite recent advances in the recovery of dynamic signatures from static signatures [48]- [51], the last type of method still an open issue [7].…”

“…The fourth behavioral class category is neuromotor theory [18], [34], [35], [39], [43], [44], [46], which considers a set of muscles, skeletal parts, eyes, and the central nervous system in creating signatures. In this case, the brain stores the signature generation plan and sends electric impulses to the eyes and to specific muscles, allowing the signature plan to be executed by a series of specific muscular contractions and articulatory movements [46].…”

“…Most neuromotor methods are not concerned with stroke sequences. However, some of them are mainly focused on the signature trajectory plan [34], [43]. This plan determines the distribution and sequence of strokes which are used to create a new signature.…”

“…To simulate the desired motor effects, most neuromotor methods use a grid to map the distribution of strokes or characters on the written surface. Different architectures (hexagonal [34], [43], quadrangular [46], and sinusoidal [18]) have been investigated for generating the desired deformations. In [34], the authors showed that the grid density is directly related to the alphabet used to sign.…”