Logo image
Reference selection for offline writer-dependent signature verification using a siamese convolutional neural network
Conference paper

Reference selection for offline writer-dependent signature verification using a siamese convolutional neural network

Ming-I Lo, Tsung-Yu Lu, Er-Hao Chen and Yeong-Luh Ueng
Proceedings of SPIE - The International Society for Optical Engineering, Vol.11878, 1187823
2021

Abstract

Convolutional neural networks Reference Selection Siamese network Signature verification Electronic Optical and Magnetic Materials Condensed Matter Physics Computer Science Applications Applied Mathematics Electrical and Electronic Engineering
This paper focuses on offline writer-dependent signature verification using a Siamese convolutional neural network. A Siamese network is comprised of equal-weighted twin networks that can be trained to learn a feature space in which similar observations are juxtaposed. To reduce the impact of the high intra-variability of the signature and ensure that the Siamese network is able to learn more effectively, we propose a method of selecting a Reference (REF). Using the proposed reference selection, the accuracy can be increased by 6.4%. By utilizing the GPDS-160 signature data-set, the designed system is able to achieve an accuracy of 94.5%, which is a better result than that achieved by current state-of-the-art writer-dependent techniques.

Metrics

1 Record Views

Details

Logo image