Fast on-line signature recognition based on VQ with time modeling

TL;DR

This paper introduces a multi-section vector quantization method for on-line signature recognition that achieves high accuracy and efficiency, outperforming existing methods while reducing computational and storage requirements.

Contribution

The paper presents a novel multi-section vector quantization approach that enhances on-line signature recognition performance and efficiency, with improved privacy features.

Findings

Achieves 99.76% identification rate on MCYT database.

Reduces computational requirement by 47 times compared to DTW.

Attains 100% identification rate on SVC database.

Abstract

This paper proposes a multi-section vector quantization approach for on-line signature recognition. We have used the MCYT database, which consists of 330 users and 25 skilled forgeries per person performed by 5 different impostors. This database is larger than those typically used in the literature. Nevertheless, we also provide results from the SVC database. Our proposed system outperforms the winner of SVC with a reduced computational requirement, which is around 47 times lower than DTW. In addition, our system improves the database storage requirements due to vector compression, and is more privacy-friendly as it is not possible to recover the original signature using the codebooks. Experimental results with MCYT provide a 99.76% identification rate and 2.46% EER (skilled forgeries and individual threshold). Experimental results with SVC are 100% of identification rate and 0% (individual threshold) and 0.31% (general threshold) when using a two-section VQ approach.