METHOD AND SYSTEM FOR VERIFYING DYNAMIC HANDWRITING AND SIGNATURES BY MEANS OF DEEP LEARNING

摘要

Method and system for verifying dynamic handwriting and signatures by means of deep learning. The method comprises the following steps: extraction of temporal functions (110) from a set of samples consisting of at least one recorded sample (Si) belonging to a certain identity and a doubted test sample (ST), obtaining at least one recorded pattern (TFi) and a test pattern (TFT); temporal alignment (120) of the at least one recorded pattern (TFi) with the test pattern (TFT), obtaining at least one aligned recorded pattern (TAFi) and an aligned test pattern (TAFT); comparison of the aligned patterns (TAFi, TAFT) by using a previously trained recurrent neural network (130), obtaining a similarity measure (132) between the at least one recorded sample (Si) and the test sample (ST); and verification of the identity (140) of the test sample (ST) based on a comparison of the similarity measure (132) with a threshold value.