Recurrent Few-Shot model for Document Verification

TL;DR

This paper introduces a recurrent few-shot model designed for document verification that effectively detects forgeries even with limited data and variable image quality, addressing key challenges in ID and travel document authentication.

Contribution

The paper proposes a novel recurrent-based few-shot model that enhances robustness to resolution variability and generalizes to unseen document classes.

Findings

Good performance on SIDTD dataset

Effective detection of forged documents

Robustness to low-resolution images

Abstract

General-purpose ID, or travel, document image- and video-based verification systems have yet to achieve good enough performance to be considered a solved problem. There are several factors that negatively impact their performance, including low-resolution images and videos and a lack of sufficient data to train the models. This task is particularly challenging when dealing with unseen class of ID, or travel, documents. In this paper we address this task by proposing a recurrent-based model able to detect forged documents in a few-shot scenario. The recurrent architecture makes the model robust to document resolution variability. Moreover, the few-shot approach allow the model to perform well even for unseen class of documents. Preliminary results on the SIDTD and Findit datasets show good performance of this model for this task.