New Benchmarks for Barcode Detection Using Both Synthetic and Real Data

Zharkov, Andrey; Vavilin, Andrey; Zagaynov, Ivan

doi:10.1007/978-3-030-57058-3_34

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Success in training neural networks heavily depends on the quality of the set of images they are trained on, and these have usually been taken as sharp, still pictures under good lighting conditions. In some cases, they have even been synthetically generated by overlapping undistorted barcodes on real images [30,31].…”

Section: Remaining Challengesmentioning

confidence: 99%

An Encoder–Decoder Architecture within a Classical Signal-Processing Framework for Real-Time Barcode Segmentation

Gómez-Cárdenes

Marichal-Hernández

Son

et al. 2023

Sensors

View full text Add to dashboard Cite

In this work, two methods are proposed for solving the problem of one-dimensional barcode segmentation in images, with an emphasis on augmented reality (AR) applications. These methods take the partial discrete Radon transform as a building block. The first proposed method uses overlapping tiles for obtaining good angle precision while maintaining good spatial precision. The second one uses an encoder–decoder structure inspired by state-of-the-art convolutional neural networks for segmentation while maintaining a classical processing framework, thus not requiring training. It is shown that the second method’s processing time is lower than the video acquisition time with a 1024 × 1024 input on a CPU, which had not been previously achieved. The accuracy it obtained on datasets widely used by the scientific community was almost on par with that obtained using the most-recent state-of-the-art methods using deep learning. Beyond the challenges of those datasets, the method proposed is particularly well suited to image sequences taken with short exposure and exhibiting motion blur and lens blur, which are expected in a real-world AR scenario. Two implementations of the proposed methods are made available to the scientific community: one for easy prototyping and one optimised for parallel implementation, which can be run on desktop and mobile phone CPUs.

show abstract

Section: Remaining Challengesmentioning

confidence: 99%

An Encoder–Decoder Architecture within a Classical Signal-Processing Framework for Real-Time Barcode Segmentation

Gómez-Cárdenes

Marichal-Hernández

Son

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The dataset may comprise the original photos taken by mobile phone cameras, industrial cameras, and images captured from video sequences [52]. Some of them are barcode images downloaded from search engines (e.g., Google and Baidu) [47], document scans [57], as well as websites [8] before all images were further adjusted by the researchers. From this aspect, we could not suggest which private datasets are most useful, as private datasets rely heavily on the criteria of the data collection phase.…”

Section: Rq2: "What Datasets Were Used In the Literature?"mentioning

confidence: 99%

Deep Learning in Barcode Recognition: A Systematic Literature Review

2022

View full text Add to dashboard Cite

The use of deep learning (DL) for barcode recognition and analysis has achieved remarkable success and has attracted great attention in various domains. Unlike other barcode recognition methods, DL-based approaches can significantly improve the speed and accuracy of both barcode detection and decoding. However, after almost a decade of progress, the current status of DL-based barcode recognition has yet to be thoroughly explored. Specifically, summaries of key insights and gaps remain unavailable in the literature. Therefore, this study aims to comprehensively review recent applications of DL methods in barcode recognition. We mainly conducted a well-constructed systematic literature review (SLR) approach to collect relevant articles and evaluate and summarize the state of the art. This study's contributions are threefold. First, the paper highlights new DL approaches' applicability to barcode localization and decoding processes and their potential to either reduce the time required or provide higher quality. Second, another main finding of this study signifies an increasing demand for public and specific barcode datasets that allow DL methods to learn more efficiently in the big data era. Finally, we conclude with a discussion on the crucial challenges of DL with respect to barcode recognition, incorporating promising directions for future research development.

show abstract

A Review of 1D Barcode Localization Algorithms in Complex Backgrounds

李

2024

JISP

View full text Add to dashboard Cite

New Benchmarks for Barcode Detection Using Both Synthetic and Real Data

Cited by 3 publications

References 15 publications

An Encoder–Decoder Architecture within a Classical Signal-Processing Framework for Real-Time Barcode Segmentation

An Encoder–Decoder Architecture within a Classical Signal-Processing Framework for Real-Time Barcode Segmentation

Deep Learning in Barcode Recognition: A Systematic Literature Review

A Review of 1D Barcode Localization Algorithms in Complex Backgrounds

Contact Info

Product

Resources

About