On the Use of Edge Features and Exponential Decaying Number of Nodes in the Hidden Layers for Handwritten Signature Recognition

Abstract

Handwritten signatures are playing an important role in finance, banking and education and more because it is considered the “seal of approval” and remains the most preferred means of authentication. In this paper, an offline handwritten signature authentication algorithm is proposed using the edge features and deep feedforward neural network (DFNN). The number of hidden layers in DFNN is configured to be at least one layer and more. In this paper, an exponential decaying number of nodes in the hidden layers was proposed to achieve better recognition rate with reasonable training time. Of the six edge algorithms evaluated, Roberts operator and Canny edge detectors were found to produce better recognition rate. Results showed that the proposed exponential decaying number of nodes in the hidden layers outperform other structure. However, more training data was required so that the proposed DFNN structure could have more efficient learning.