They design a way to facilitate the reading of QR codes on irregular surfaces

They design a way to facilitate the reading of QR codes on irregular surfaces

QR codes (quick response) are a variation of the typical barcode, capable of collecting information in computer language, in a two-dimensional array of black and white pixels, when scanned with a reading device. They facilitate access to data of interest, save time and resources such as paper, and have revolutionized the way in which the user accesses information in the digital sphere.

However, sometimes it is difficult to scan a barcode or QR code correctly.

A new system helps solve that problem.

The new system is general in nature, does not depend absolutely on the underlying topography, and is applicable in QR codes that we can find on tubular surfaces (bottles), food trays, etc. This is the first technological proposal capable of combining a general methodology and two-dimensional barcodes to facilitate the recognition of digital information.

The first author of the work is Professor Ismael Benito, from the University of Barcelona (UB), and from those of Computer Science, Multimedia and Telecommunications Studies at the Open University of Catalonia (Universitat Oberta de Catalunya, UOC). Cristian Fàbrega and Joan Daniel Prades, professors at the Faculty of Physics and the Institute of Nanoscience and Nanotechnology of the UB (IN2UB), are co-authors of the research, as well as the experts Hanna Lizarzaburu-Aguilar and David Martínez Carpena, in the Faculty of Mathematics and Informatics of the UB. All the authors have participated in different positions in the creation of ColorSensing, SL, a spin-off company of the UB in the field of intelligent labeling.

The occasional difficulty in reading a barcode or QR code is due, “first of all, to the quality of the image. Although many people today have access to good digital photography cameras, they are not always able to capture the QR image well. Secondly, the quality of the QR code printing and the colors used, with good contrast, is sometimes not satisfactory. Finally, if the printing surface is not flat enough and is not located parallel to the capture plane, it will also be difficult to capture the code information,” explains Benito.

«For example, all these factors come into play when we try to capture a Bicing QR with the mobile application: the surface is not flat — it is a cylinder — and if we try to capture the QR very close, the deformation of the surface becomes evident and the reading fails—5-10 centimeters—; If we move too far away, the QR becomes too small and the capture is not good (1 meter); If we are in an intermediate range, the apparent distortion of the surface is reduced and the quality is suitable for capturing it—30-50 centimeters—”, explains Benito.

The work, which is part of the doctoral thesis prepared by Ismael Benito at the UB, presents a new algorithm that takes advantage of the characteristics of the QR—that is, the internal patterns of the code—to extract the underlying surface on which it is positioned. the code.

The texture of this surface is recovered through a general adjustment based on mathematical functions known as splines, which allow adjusting the topography of the surface at a local level. Benito points out that “they are functions that adapt locally to the ups and downs of the surface, and form a technique widely used originally in fields such as geology or photographic editing to adjust or generate deformations on surfaces.”

The authors of the new study have managed to develop a mathematical solution to make it easier to read these two-dimensional codes on deformed surfaces, such as courier packages or food trays. (Image: Pattern Recognition Letters. CC BY)

There are still many pending technological challenges to improve the entire QR code recognition process. In the case of commercial applications activated by the user’s code reader, the expert details that “the main challenge is being able to provide correct and reliable readings. We are also working hard to ensure that the codes cannot be attacked using modification techniques, for example, with a fake URL that can capture data with small modifications to the code. In the case of the industry, in which captures are carried out in controlled environments, the main challenge is to reduce the speed of capture,” says the expert.

It is worth remembering that ColorSensing, created at the UB in 2020 by Professor Joan Daniel Prades, from the Faculty of Physics and the INN, and by María Eugenia Martín, now general director of this emerging company, won the 2023 Metropolitan Business Innovation Award for having developed smart labeling to reduce food waste. Likewise, in 2022 it received the Senén Vilaró Award from the UB for the best innovative company, being distinguished in the Sustainability Awards 2022 within the intelligent and active packaging category. Another of the firm’s scientific achievements is the patent granted in the United States and Europe, whose promoters are Ismael Benito (UB and UOC), Olga Casals (UB), Cristian Fàbrega (UB), Joan Daniel Prades (UB and Technical University from Braunschweig, TUB, in Germany) and Andreas Waag (TUB).

Benito and his colleagues present the technical details of this advance in the academic journal Pattern Recognition Letters, under the title “Reading QR Codes on challenging surfaces using thin-plate splines.” (Source: UB)