A neural network approach to off-line signature verification using directional PDF

作者: J.-P. Drouhard , R. Sabourin , M. Godbout

DOI: 10.1016/0031-3203(95)00092-5

关键词: Classifier (UML)Artificial neural networkMathematicsArtificial intelligencePattern recognitionDecision ruleMargin classifierShape factorBackpropagationOff lineProbability density function

摘要: A neural network approach is proposed to build the first stage of an Automatic Handwritten Signature Verification System. The directional Probability Density Function was used as a global shape factor and its discriminating power enhanced by reducing cardinality via filtering. Various experimental protocols were implement backpropagation (BPN) classifier. comparison, on same database with decision rule, shows that BPN classifier clearly better than threshold compares favourably k-Nearest-Neighbour

参考文章(27)
Eric P. Smith, Morton Nadler, Pattern recognition engineering ,(1993)
Robert Sabourin, Réjean Plamondon, Guy Lorette, Off-line Identification With Handwritten Signature Images: Survey and Perspectives Springer, Berlin, Heidelberg. pp. 219- 234 ,(1992) , 10.1007/978-3-642-77281-8_10
Structured Document Image Analysis Springer-Verlag New York, Inc.. ,(1992) , 10.1007/978-3-642-77281-8
Keinosuke Fukunaga, Introduction to statistical pattern recognition (2nd ed.) Academic Press Professional, Inc.. ,(1990)
Ash, Dynamic node creation in backpropagation networks international joint conference on neural network. pp. 623- ,(1989) , 10.1109/IJCNN.1989.118509
Alianna J. Maren, Dan Jones, Stanley Franklin, Configurating and optimizing the back-propagation network Handbook of neural computer applications. pp. 237- 250 ,(1990) , 10.1016/B978-0-12-546090-3.50019-X