Recognition of Perspective Distorted QR Codes with a Partially Damaged Finder Pattern in Real Scene Images

Karrach, Ladislav; Pivarčiová, Elena; Božek, Pavol

doi:10.3390/app10217814

Cited by 15 publications

(17 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…El uso de estos dos colores asegura un alto contraste entre los módulos y el fondo permitiendo su mejor lectura y, aunque originalmente se diseñaron en blanco y negro, se puede utilizar cualquier color siempre que se conserve el contraste entre los módulos para así poder ser detectados durante el proceso de binarización (11). Las diferencias entre el color y el brillo de los módulos permiten la conversión al sistema binario (binarización) donde los módulos claros corresponden al símbolo cero (0) y los oscuros al uno (1) (Figura 4) (12). El módulo es la unidad elemental y su cantidad dentro de un símbolo QR va a depender de su versión.…”

Section: La Unidad Elementalunclassified

QR Codes in Medical Education - Part 1 An Analog - Digital Bridge

Spinelli¹,

Dreizzen²

2021

An. Fac. Cienc. Méd. (Asunción)

View full text Add to dashboard Cite

With the rapid development of Information and communication technologies and the widespread use of the Internet and smartphones, the QR codes (stands for quick response code) are becoming a promising tool for connecting offline and online services. This article is the first in a series of two articles that aim to contextualize the use of QR codes in health education. This will allow the educators to develop the skills necessary for its creation and use in medical education. Successful implementation of the QR Code in health education requires a knowledge of certain basic information about both the QR Code itself and the necessary requirements for the use of this type of symbology. This first article presents an overview of the current state of the art of the QR codes and discusses in brief the structure, symbology, versions, properties and the requirements for the use of this type of symbology. In the second part of this series we will describe the main aspects related to: custom QR Code with Logo, static and dynamic codes, and the different tools and applications necessary to generate and decode a QR code as well as how to apply it in different educational contexts of Augmented Reality. The final purpose of these two articles is to ensure that all educators feel familiar with this technology and can incorporate it into the educational material used in the teaching-learning process, both traditional classroom and online courses.

show abstract

Section: La Unidad Elementalunclassified

QR Codes in Medical Education - Part 1 An Analog - Digital Bridge

Spinelli¹,

Dreizzen²

2021

An. Fac. Cienc. Méd. (Asunción)

View full text Add to dashboard Cite

show abstract

“…Three detected FIPs allow identifying orientation of the code in the scene. Further improvements to the basic line-scan approach involves compensation of geometric distortions and partially corrupted finder patterns [ 24 ].…”

Section: Introductionmentioning

confidence: 99%

Performance of QR Code Detectors near Nyquist Limits

Skurowski

Nurzynska

Pawlyta

et al. 2022

Sensors

View full text Add to dashboard Cite

For the interacting with real world, augmented reality devices need lightweight yet reliable methods for recognition and identification of physical objects. In that regard, promising possibilities are offered by supporting computer vision with 2D barcode tags. These tags, as high contrast and visually well-defined objects, can be used for finding fiducial points in the space or to identify physical items. Currently, QR code readers have certain demands towards the size and visibility of the codes. However, the increase of resolution of built-in cameras makes it possible to identify smaller QR codes in the scene. On the other hand, growing resolutions cause the increase to the computational effort of tag location. Therefore, resolution reduction in decoders is a common trade-off between processing time and recognition capabilities. In this article, we propose the simulation method of QR codes scanning near limits that stem from Shannon’s theorem. We analyze the efficiency of three publicly available decoders versus different size-to-sampling ratios (scales) and MTF characteristics of the image capture subsystem. The MTF we used is based on the characteristics of real devices, and it was modeled using Gaussian low-pass filtering. We tested two tasks—decoding and locating-and-decoding. The findings of the work are several-fold. Among others, we identified that, for practical decoding, the QR-code module should be no smaller than 3–3.5 pixels, regardless of MTF characteristics. We confirmed the superiority of Zbar in practical tasks and the worst recognition capabilities of OpenCV. On the other hand, we identified that, for borderline cases, or even below Nyquist limit where the other decoders fail, OpenCV is still capable of decoding some information.

show abstract

“…Two-dimensional barcode symbols have been widely used in automated identification applications, such as industrial components retrospect [1], mobile robots [2], and Construction Safety Management [3]. Compared to the 1D barcode, 2D barcode symbols have more popular advantages, such as large data capacity, compact size, and strong fault tolerance [4].…”

Section: Introductionmentioning

confidence: 99%

Data Extraction Method for Industrial Data Matrix Codes Based on Local Adjacent Modules Structure

Liao

2022

Applied Sciences

View full text Add to dashboard Cite

A 2D barcode is a reliable way to provide lifetime traceability of parts that are exposed to harsh environments. However, there are considerable challenges in adopting mobile cameras to read symbols directly marked on metal surfaces. Images captured by mobile cameras are usually of low quality with poor contrast due to the reflective surface of 2D barcode symbols. To deal with this problem, a novel laser-marked Data Matrix symbols reading method based on deep learning is proposed for mobile phone captured images. Utilizing the barcode module features, we train different convolutional neural network (CNN) models to learn the colors of two adjacent modules of a Data Matrix symbol. Depending on whether the colors of the two adjacent modules are the same or not, an edge image is transformed from a square grid, which is the same size as the barcode. A correction method based on the KM algorithm is used to get a corrected edge image, which helps to reconstruct the final barcode image. Experiments are carried out on our database, and the results show that the proposed algorithm outperforms in high accuracy of barcode recognition.

show abstract

Recognition of Perspective Distorted QR Codes with a Partially Damaged Finder Pattern in Real Scene Images

Cited by 15 publications

References 21 publications

QR Codes in Medical Education - Part 1 An Analog - Digital Bridge

QR Codes in Medical Education - Part 1 An Analog - Digital Bridge

Performance of QR Code Detectors near Nyquist Limits

Data Extraction Method for Industrial Data Matrix Codes Based on Local Adjacent Modules Structure

Contact Info

Product

Resources

About