Online signature verification by spectrogram analysis

Abstract

The concept of electronic signatures emerged decades ago, however they are still not prevalent due to lack of reliable infrastructure. Although the signatures are hard to perfectly imitate, it is simple with an image editing software to copy the original signature and paste on a document. On the other hand, technological developments of touchscreens may create a new era by utilizing simple interfaces which would be recording and validating the electronic signatures with biometric features. Therefore, in this paper, we propose a novel online signature analysis methodology for touchscreens that starts with signing an interface consisting of a signature silhouette. The frequency spectrum along the signing process is stealthily extracted and spectrograms are created by short-time Fourier transforms. Since the spectrograms are found as RGB images, providing valuable information about frequency vs time, grid histograms are formed by quantization for the real signature sample. Given the discrimination purposes, a fuzzified surface is designed for computing closeness of grid histograms.