MRZ code extraction from visa and passport documents using convolutional neural networks
arXiv:2009.05489 · doi:10.1007/s10032-021-00384-2
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.
arXiv commentThis is a preprint of https://doi.org/10.1007/s10032-021-00384-2
References in corpus (5)
- SSD: Single Shot MultiBox Detector
- TextBoxes++: A Single-Shot Oriented Scene Text Detector
- MIDV-500: A Dataset for Identity Documents Analysis and Recognition on Mobile Devices in Video Stream
- Detecting Multi-Oriented Text with Corner-based Region Proposals
- Optical Font Recognition in Smartphone-Captured Images, and its Applicability for ID Forgery Detection