Signature verification approach using fusion of hybrid texture features

Abstract

In this paper, a writer-dependent signature verification method is proposed. Two different types of texture features, namely discrete wavelet and local quantized patterns (LQP) features, are employed to extract two kinds of transform and statistical-based information from signature images. For each writer, two separate signature models, corresponding to each set of LQP and wavelet features, using one-class support vector machines (SVMs) are created to obtain two different authenticity scores for a given signature. Finally, a score-level classifier fusion based on the average method is performed to integrate the scores obtained from the two one-class SVMs and achieve the final verification score. To train the one-class SVMs in the proposed system, only genuine signatures are considered. The proposed signature verification method was tested using four different publicly available datasets to demonstrate the generality of the proposed method. The evaluation results indicate that the proposed system outperforms other existing systems in the literature. © 2019, Springer-Verlag London Ltd., part of Springer Nature.