On-line signature verification using LPC cepstrum and neural networks
- 1 February 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
- Vol. 27 (1) , 148-153
- https://doi.org/10.1109/3477.552197
Abstract
An on-line signature verification scheme based on linear prediction coding (LPC) cepstrum and neural networks is proposed. Cepstral coefficients derived from linear predictor coefficients of the writing trajectories are calculated as the features of the signatures. These coefficients are used as inputs to the neural networks. A number of single-output multilayer perceptrons (MLPs), as many as the number of words in the signature, are equipped for each registered person to verify the input signature. If the summation of output values of all MLPs is larger than the verification threshold, the input signature is regarded as a genuine signature; otherwise, the input signature is a forgery. Simulations show that this scheme can detect the genuineness of the input signatures from a test database with an error rate as low as 4%Keywords
This publication has 8 references indexed in Scilit:
- Toward generating neural network structures for function approximationNeural Networks, 1994
- Networks for approximation and learningProceedings of the IEEE, 1990
- Learning algorithms for perceptions using back-propagation with selective updatesIEEE Control Systems Magazine, 1990
- Signature recognition through spectral analysisPattern Recognition, 1989
- Automatic signature verification and writer identification — the state of the artPattern Recognition, 1989
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- An Improved Regional Correlation Algorithm for Signature Verification Which Permits Small Speed Changes Between Handwriting SegmentsIBM Journal of Research and Development, 1983
- Automatic Signature Verification Based on AccelerometryIBM Journal of Research and Development, 1977