A Review of Signature Recognition Using Machine Learning
Elizabeth Ann Soelistio, Rafael Edwin Hananto Kusumo, Zevira Varies Martan, Edy Irwansyah
Abstract
Signatures have been used for years for transactions and consenting to responsibilities. Yet, online or offline, signatures can easily be falsified as there are no security measures in place to prevent this. Numerous researches have been carried out to find the most accurate and reliable signature recognition and verification system. This study examines the two problems previously mentioned. A primary goal of this study is to determine the best algorithms for recognizing signatures based on the signature type. This systematic literature review is conducted using a PRISMA flow diagram. The results indicate that offline signatures mostly use Convolutional Neural Networks (CNN) for their recognition, while online signatures use Recurrent Neural Networks (RNN) with other architectures.