Online Signature Verification Using Vector Quantization and Hidden Markov Model

Abstract

In this paper an on-line signature verification system, using vector quantization and Hidden Markov Model (VQ-HMM) is presented. After the signature acquisition, a Chebichef filter is used for noise reduction, and size and phase normalization is performed using Fourier transform. Each signature is segmented and mean velocity, acceleration and pressure are used as extracted features. K-means clustering is used for generation a codebook and VQ generates a code word for each signature. These code words are used as observation vectors in training and recognition phase. HMM models are trained using Baum Welch algorithm. In the verification phase, the forward algorithm is used. The Threshold used in the verification phase is a function of the minimum probability in training phase. Equal Error Rate obtained from this system is 14%.