Deep Neural Network For Online Writer Identification Using Beta-Elliptic Model

The online writer identification is a required component in many applications of Computer vision and Pattern Recognition. The offline writer identification is more developed in literature due to the use of traditional system based on Image Processing. There is a lack of works done in the case of online writer identification. In this paper, we propose a novel method to text independent writer identification from online handwriting. Our proposed method is based on the use of Beta-elliptic model that computes efficiently on real time writing movements in online handwriting by involving simultaneously its both profile entities: the Beta impulses and the elliptic arcs. The information provided by the feature extraction is used in a Deep Neural Network as classifier. The obtained results show that the proposed online writer identification method is worth to receive further exploration in capturing the writer's individual. The use of the Deep Neural Network provides more robustness to identification of writers.