What question did this study set out to answer?

To develop an algorithm for verifying signatures on a touch-sensitive pad using a Siamese neural network.

Signature Verification Using a “Siamese” Time Delay Neural Network

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates accurate signature verification using a Siamese network, highlighting potential for security applications.

To develop an algorithm for verifying signatures on a touch-sensitive pad using a Siamese neural network.
Developed a Siamese time delay neural network for signature verification.
Trained the network on pairs of signatures to measure similarity.
Compared feature vectors of input signatures with stored signature representations for verification.
Signatures closer than a set threshold were accepted and classified as genuine.
The algorithm shows high accuracy in distinguishing between authentic signatures and forgeries.

Bromley et al. (1993) studied this question.

View Full Paper

Ask AI

Bookmark