MIDV-2019: Challenges of the modern mobile-based document OCR

TL;DR

This paper introduces the MIDV-2019 dataset, a challenging collection of mobile-captured identity document videos with distortions and low lighting, to advance OCR research.

Contribution

The paper presents a new dataset, MIDV-2019, addressing key issues like distortions and lighting variations not covered in previous datasets.

Findings

Baseline OCR performance varies significantly across conditions.

The dataset highlights challenges in mobile document OCR.

Provides a benchmark for future research.

Abstract

Recognition of identity documents using mobile devices has become a topic of a wide range of computer vision research. The portfolio of methods and algorithms for solving such tasks as face detection, document detection and rectification, text field recognition, and other, is growing, and the scarcity of datasets has become an important issue. One of the openly accessible datasets for evaluating such methods is MIDV-500, containing video clips of 50 identity document types in various conditions. However, the variability of capturing conditions in MIDV-500 did not address some of the key issues, mainly significant projective distortions and different lighting conditions. In this paper we present a MIDV-2019 dataset, containing video clips shot with modern high-resolution mobile cameras, with strong projective distortions and with low lighting conditions. The description of the added data is presented, and experimental baselines for text field recognition in different conditions. The dataset is available for download at ftp://smartengines.com/midv-500/extra/midv-2019/.