Synthetic off-line signature image generation
- 1 June 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper proposes a novel methodology to generate static/off-line signatures of new identities. The signature of the new synthetic identity is obtained particularizing the random variables of a statistical distribution of global signature properties. The results mimic real signature shapes and writing style properties, which are estimated from static signature databases. New instances, as well as forgeries, from the synthetic identities are obtained introducing a natural variability from the synthetic individual properties. As additional novelty, an ink deposition model based on a ballpoint is developed for realistic static signature image generation. The range of the static signature generator has been established matching the performance obtained with the synthetic databases and those obtained with two public databases.Keywords
This publication has 14 references indexed in Scilit:
- Synthetic on-line signature generation. Part II: Experimental validationPattern Recognition, 2012
- Robustness of Offline Signature Verification Based on Gray Level FeaturesIEEE Transactions on Information Forensics and Security, 2012
- What Is a Savitzky-Golay Filter? [Lecture Notes]IEEE Signal Processing Magazine, 2011
- Signature Analysis, Verification and Synthesis in Pervasive EnvironmentsSeries in Machine Perception and Artificial Intelligence, 2007
- Ink-Deposition Model: The Relation of Writing and Ink Deposition ProcessesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Improving face authentication using virtual samplesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Least Squares Support Vector MachinesPublished by World Scientific Pub Co Pte Ltd ,2002
- Virtual brush: a model-based synthesis of Chinese calligraphyComputers & Graphics, 2000
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995
- Trajectory formation and handwriting: A computational modelBiological Cybernetics, 1982