Methods of machine-readable zone recognition results post-processing

Petrova, Olga O.; Bulatov, Konstantin B.

doi:10.1117/12.2522792

Cited by 8 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The problem statement for language-dependent recognition results correction based on a combination of hypotheses (encoded in the text field recognition result   (I)) language model  and an error model which defines possible modifications, is presented in [96] using WFSTs (Weighted Finite-State Transducers). An alternative approach that is based on representing  as a validation grammar with a custom predicate is described in [97,98].…”

Section: D) Collecting the Document Recognition Resultsmentioning

confidence: 99%

Towards a unified framework for identity documents analysis and recognition

Bulatov¹,

Bezmaternykh²,

Nikolaev

et al. 2022

Computer Optics

View full text Add to dashboard Cite

Identity documents recognition is far beyond classical optical character recognition problems. Automated ID document recognition systems are tasked not only with the extraction of editable and transferable data but with performing identity validation and preventing fraud, with an increasingly high cost of error. A significant amount of research is directed to the creation of ID analysis systems with a specific focus for a subset of document types, or a particular mode of image acquisition, however, one of the challenges of the modern world is an increasing demand for identity document recognition from a wide variety of image sources, such as scans, photos, or video frames, as well as in a variety of virtually uncontrolled capturing conditions. In this paper, we describe the scope and context of identity document analysis and recognition problem and its challenges; analyze the existing works on implementing ID document recognition systems; and set a task to construct a unified framework for identity document recognition, which would be applicable for different types of image sources and capturing conditions, as well as scalable enough to support large number of identity document types. The aim of the presented framework is to serve as a basis for developing new methods and algorithms for ID document recognition, as well as for far more heavy challenges of identity document forensics, fully automated personal authentication and fraud prevention.

show abstract

Section: D) Collecting the Document Recognition Resultsmentioning

confidence: 99%

Towards a unified framework for identity documents analysis and recognition

Bulatov¹,

Bezmaternykh²,

Nikolaev

et al. 2022

Computer Optics

View full text Add to dashboard Cite

show abstract

“…For the recognition we use a lightweight segmentation and recognition neural network [19] [20] without any special training and setup for price tags fonts. Post-processing is called to normalize recognized value to known price tag format [21].…”

Section: Control Flowchartmentioning

confidence: 99%

A low computational approach for price tag recognition

Aliev¹,

Nikolaev

Kunina³

et al. 2020

Twelfth International Conference on Machine Vision (ICMV 2019)

View full text Add to dashboard Cite

In this work we discuss the task of search, localization and recognition of price zone within a photograph of the price tag. The task is being addressed for the case when image is acquired by small-scale digital camera and calculation device has significant resource constraints. The proposed approach is based on Niblack binarization algorithm, analysis and clasterization of connected components in conditions of known price tag geometrical model. The algorithm was tested on a private dataset and has shown high quality.

show abstract

“…(Chernyshova et al 2019) explored optical font recognition for forgery detection in passport MRZs. (Petrova and Bulatov 2019) discuss methods for correcting or post-processing passport MRZ recognition results. (Hartl, Arth, and Schmalstieg 2015) present an algorithm for reading MRZ images on mobile devices, achieving an MRZ detection rate of 88.18% with 5 frames and 56.1% with single frame, along with a character reading rate of 98.58%.…”

Section: Passport Mrz Detection and Extractionmentioning

confidence: 99%

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

Liu,

James,

Gupta

et al. 2020

Preprint

View full text Add to dashboard Cite

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.

show abstract

Methods of machine-readable zone recognition results post-processing

Cited by 8 publications

References 3 publications

Towards a unified framework for identity documents analysis and recognition

Towards a unified framework for identity documents analysis and recognition

A low computational approach for price tag recognition

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

Contact Info

Product

Resources

About