Summary of Neural Network Modelling Of Kinematic and Dynamic Features For Signature Verification, by Moises Diaz et al.
Neural network modelling of kinematic and dynamic features for signature verification
by Moises Diaz, Miguel A. Ferrer, Jose Juan Quintana, Adam Wolniakowski, Roman Trochimczuk, Konstantsin Miatliuk, Giovanna Castellano, Gennaro Vessio
First submitted to arxiv on: 26 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach to estimating online signature parameters is proposed, leveraging human characteristics to broaden the applicability of automatic signature verification. Kinematic and dynamic features have been previously explored, but accurately measuring arm and forearm torques remains a challenge. Two methods are presented for estimating angular velocities, positions, and force torques: a physical robotic arm-based approach and a cost-effective neural network-based method. The findings demonstrate that a simple neural network model can extract effective parameters for signature verification, generalizing well across datasets including MCYT300, BiosecurID, Visual, Blind, OnOffSigDevanagari 75, and OnOffSigBengali 75. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Online signature parameters are important for making sure electronic signatures are real. Scientists used to think that just measuring how the arm moves was enough, but they realized it’s harder than that. They came up with two new ways to measure things like arm strength and movement. One way is to use a robotic arm to move like a person signing their name. The other way is to use a special kind of computer program called a neural network. The results show that this simple computer program can help make sure signatures are real. They tested it with lots of different datasets and it worked well. |
Keywords
* Artificial intelligence * Neural network
