Forgetting of unused classes in missing data environment using automatically generated data: Application to on-line handwritten gesture command recognition

Režnáková, Marta; Tencer, Lukas; Plamondon, Réjean; Cheriet, Mohamed

doi:10.1016/j.patcog.2017.08.007

Cited by 9 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main idea is that the neuromuscular system involved in the production of an aimed movement can be considered as a linear system made up of coupled subsystems, and the impulse response of such a system converges toward a lognormal function. The ΣΛ model has been successfully used for synthesizing stroke gestures [14], [16], [34] and signatures [10], [35], [36], among other types of human movements [15], [37] with high levels or realism. In addition, the ΣΛ model is the only approach we are aware of that can generate human-like generic spatiotemporal handwriting sequences.…”

Section: Related Workmentioning

confidence: 99%

Human or Machine? It Is Not What You Write, But How You Write It

Leiva¹,

Diaz²,

Ferrer³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Online fraud often involves identity theft. Since most security measures are weak or can be spoofed, we investigate a more nuanced and less explored avenue: behavioral biometrics via handwriting movements. This kind of data can be used to verify whether a user is operating a device or a computer application, so it is important to distinguish between human and machine-generated movements reliably. For this purpose, we study handwritten symbols (isolated characters, digits, gestures, and signatures) produced by humans and machines, and compare and contrast several deep learning models. We find that if symbols are presented as static images, they can fool state-ofthe-art classifiers (near 75% accuracy in the best case) but can be distinguished with remarkable accuracy if they are presented as temporal sequences (95% accuracy in the average case). We conclude that an accurate detection of fake movements has more to do with how users write, rather than what they write. Our work has implications for computerized systems that need to authenticate or verify legitimate human users, and provides an additional layer of security to keep attackers at bay.

show abstract