Offline Signature Verification Using Textural Descriptors

Ismail Hadjadj, Abdeljalil Gattal, Chawki Djeddi, Mouloud Ayad, Imran Siddiqi, Faycel Abass
  • January 2019, Springer Science + Business Media
  • DOI: 10.1007/978-3-030-31321-0_16

Offline Signature Verification Using Textural Descriptors

What is it about?

Offline signature verification has been the most commonly employed modality for authentication of an individual and, it enjoys global acceptance in legal, banking and official documents. Verifying the authenticity of a signature (genuine or forged) remains a challenging problem from the perspective of computerized solutions. This paper presents a signature verification technique that exploits the textural information of a signature image to discriminate between genuine and forged signatures. Signature images are characterized using two textural descriptors, the local ternary patterns (LTP) and the oriented basic image features (oBIFs). Signature images are projected in the feature space and the distances between pairs of genuine and forged signatures are used to train SVM classifiers (a separate SVM for each of the two descriptors). When presented with a questioned signature, the decision on its authenticity is made by combining the decisions of the two classifiers. The technique is evaluated on Dutch and Chinese signature images of the ICDAR 2011 benchmark dataset and high accuracies are reported.


Dr Mouloud AYAD

In our further study on this problem, we intend to investigate other textural measures for signature verification and incorporate feature selection techniques to identify the most appropriate textural descriptors for this problem. With multiple features, sophisticated feature as well as classifier combination techniques can also be investigated such as the new approaches based on deep. Another interesting direction could be to carry out a comprehensive series of experiments by varying the number of signatures in the training set to identify the minimum number of samples required for acceptable performance for example using a more popular database.

Read Publication

The following have contributed to this page: Dr Mouloud AYAD

In partnership with: