MRZ code extraction from visa and passport documents using convolutional neural networks

TL;DR

This paper introduces a convolutional neural network-based model that accurately detects and extracts MRZ information from passport and visa images, overcoming limitations of traditional OCR methods.

Contribution

The authors developed a novel CNN model capable of extracting MRZ data from images of passports and visas regardless of orientation and size, achieving high detection and recognition accuracy.

Findings

100% MRZ detection rate

98.36% character recognition macro-f1 score

Effective on arbitrary passport and visa images

Abstract

Detecting and extracting information from Machine-Readable Zone (MRZ) on passports and visas is becoming increasingly important for verifying document authenticity. However, computer vision methods for performing similar tasks, such as optical character recognition (OCR), fail to extract the MRZ given digital images of passports with reasonable accuracy. We present a specially designed model based on convolutional neural networks that is able to successfully extract MRZ information from digital images of passports of arbitrary orientation and size. Our model achieved 100% MRZ detection rate and 98.36% character recognition macro-f1 score on a passport and visa dataset.