Method and system for identifying a user and non-transitory computer readable storage medium

A method of identifying a user, comprising:

• acquiring a signal representing a drawing input generated by an unconstrained movement of the user on an interactive surface;
• generating an image that corresponds to the signal;
• extracting static features from the image to generate an embedded vector;
• processing the signal by applying a dynamic feature extraction on the signal that registers a movement behavior of the user to generate a user behavior vector;
• and
• identifying the user by comparing the image with an identification image representing an identification drawing previously stored in association with the user, the comparing of the image with the identification image previously stored in association with the user that represents the identification drawing further includes computing a distance between the embedded vector and a plurality of template images stored in a dataset, the plurality of template images including an identification image previously acquired from the user for identification where the computed distance is below a predefined threshold;
• selecting a binary classification model with the user behavior vector, the binary classification model being a machine learning model trained to authenticate the user with behaviors vectors representative of movement behaviors;
• and
• comparing, with the binary classification model, the user behavior vector with a previously user behavior vector associated with the identification drawing.