Deep Learning in Barcode Recognition: A Systematic Literature Review

Abstract

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.