A hybrid statistical modelling, normalization and inferencing techniques of an off-line signature verification system

• Main Authors: Ahmad S.M.S., Shakil A., Faudzi M.A., Anwar R.Md., Balbed M.A.M.
• Other Authors: 24721182400
• Format: Conference paper
• Published: 2023
• Subjects: Bayesian inference; Hidden Markov Model (HMM); Computer science; Hidden Markov models; Inference engines; Probability density function; Final decision; Learning phase; Local feature; Log likelihood; Match score; Off-line signature verification; Reference models; Second layer; Statistical modelling; Statistical techniques; Three-layer; Z-score analysis; Bayesian networks
• Institution: Universiti Tenaga Nasional

This paper presents an automatic off-line signature verification system that is built using several statistical techniques .The learning phase involves the use of Hidden Markov Modelling (HMM) technique to build a reference model for each local feature extracted from a set of signature samples of a particular user. The verification phase uses three layers of statistical techniques.. The first layer involves the computation of the HMM-based log-likelihood probability match score. The second layer performs the mapping of this score into soft boundary ranges of acceptance or rejection through the use of z-score analysis and normalization function. Next Bayesian inference technique is used to arrive at the final decision of accepting or rejecting a given signature sample. � 2008 IEEE.