Signature analysis system using a convolutional neural network

Identity verification using biometric methods has been used for many years. A special case is a handwritten signature made on a digital device or piece of paper. For the digital analysis and verification of its authenticity, special methods are needed. Unfortunately, this is a rather complicated task that quite often requires complex processing techniques. In this paper, we propose a system of signatures verification consisting of two stages. In the first one, a signature pattern is created. Thanks to this, the first attempt to verify identity takes place. In the case of approval, the second stage is followed by the processing of a graphic sample containing a signature by the convolutional neural network. The proposed technique has been described, tested and discussed due to its practical use.

---

1. Authors acknowledge contribution to this project to the Diamond Grant No. 0080/DIA/2016/45 funded by the Polish Ministry of Science and Higher Education.

---

2. Track 2: Computer Science & Systems

---

3. Technical Session: 4th International Workshop on Language Technologies and Applications

---

4. Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).