An Immune Clonal Selection Algorithm for Synthetic Signature Generation

Abstract

The collection of signature data for system development and evaluation generally requires significant time and effort. To overcome this problem, this paper proposes a detector generation based clonal selection algorithm for synthetic signature set generation. The goal of synthetic signature generation is to improve the performance of signature verification by providing more training samples. Our method uses the clonal selection algorithm to maintain the diversity of the overall set and avoid sparse feature distribution. The algorithm firstly generates detectors with a segmentedr-continuous bits matching rule andP-receptor editing strategy to provide a more wider search space. Then the clonal selection algorithm is used to expand and optimize the overall signature set. We demonstrate the effectiveness of our clonal selection algorithm, and the experiments show that adding the synthetic training samples can improve the performance of signature verification.

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].…”

“…Song and Sun [17] proposed a method to duplicate dynamic signatures based on genetic algorithms. Firstly, a set of duplicates with successive stroke sections are generated.…”

“…One alternative is to use data augmentation techniques to increase the number of signatures in the feature and image space. When this process is performed in the image space, it is known as signature duplication [17]. Several signature duplication techniques have been proposed in the literature [17]- [24].…”

“…When this process is performed in the image space, it is known as signature duplication [17]. Several signature duplication techniques have been proposed in the literature [17]- [24]. In particular, techniques based on human behavior present more realistic duplicates than other approaches [18], [20], [22].…”

Multiple Generation of Bengali Static Signatures

“…Therefore, they do not create new individuals but possible signatures executed by the signers. Both in on-line [9], [10], [11], [12] and off-line [13], [14], [15], [16], [17], [18], [19], [20], the algorithms are able to generate new samples of a real user. Duplicated signatures present several advantages such as training improvement in ASV, statistically meaningful evaluations, enlarging the number of samples in a database, etc.…”