Quick response barcode deblurring via doubly convolutional neural network

Pu, Haitao; Fan, Mengbao; Yang, Jinliang; Lian, Jian

doi:10.1007/s11042-018-5802-2

Cited by 15 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although DL's significant capabilities highly benefit image processing task, DL applications seems to be overlooked with respect to the barcode decoding process. This finding highlights important opportunities to study and improve the barcode decoding process, which also echoes findings from earlier work [37].…”

Section: B Rq1: "What Type Of Barcode and DL (Cnn) Methods Were Used ...supporting

confidence: 85%

“…Moreover, past studies' findings have indicated that D-CNN's applications in barcode recognition could assist humans in precisely, accurately, and instantly detecting and decoding barcodes. It is also better able to deal with barcode recognition issues, such as blurring and distortion, than other DL techniques [36], [37]. D-CNN's abilities and advantages in barcode recognition harmonize with the requirements of real-life applications for both commercial and public sector.…”

Section: B Deep Learning (Dl) and Convolutional Neural Network (Cnns)mentioning

confidence: 99%

See 1 more Smart Citation

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

Section: B Rq1: "What Type Of Barcode and DL (Cnn) Methods Were Used ...supporting

confidence: 85%

Section: B Deep Learning (Dl) and Convolutional Neural Network (Cnns)mentioning

confidence: 99%

Deep Learning in Barcode Recognition: A Systematic Literature Review

2022

View full text Add to dashboard Cite

show abstract

“…In the future, we will continue to explore the implicit process of feature extraction by CNN and attempt to find the explicit mapping between the performance of the CNN and the role of local and global features extracted by CNN. Meanwhile, we will also research on more applications of our proposed CNNbased classification method in various fields including medical image processing, object classification, and recognition [25][26][27][28][29].…”

Section: Discussionmentioning

confidence: 99%

Automatic classification of refrigerator using doubly convolutional neural network with jointly optimized classification loss and similarity loss

Gao¹,

Lian²,

Gong³

2018

J Image Video Proc.

Self Cite

View full text Add to dashboard Cite

Modern production lines for refrigerator take advantage of automated inspection equipment that relies on cameras. As an emerging problem, refrigerator classification based on images from its front view is potentially invaluable for industrial automation of refrigerator. However, it remains an incredibly challenging task because refrigerator is commonly viewed against dense clutter in a background. In this paper, we propose an automatic refrigerator image classification method which is based on a new architecture of convolutional neural network (CNN). It resolves the hardships in refrigerator image classification by leveraging a data-driven mechanism and jointly optimizing both classification and similarity constraints. To our best knowledge, this is probably the first time that the deep-learning architecture is applied to the field of household appliance of the refrigerator. Due to the experiments carried out using 31,247 images of 30 categories of refrigerators, our CNN architecture produces an extremely impressive accuracy of 99.96%.

show abstract

“…On the other hand, a regularization approach [9] and an anisotropic total variation regularized L 1 -approximation method [36] have been proposed to address the ill-posed problem of image restoration and prevent image overfitting. In addition, doubly convolutional neural network [5] had been proposed to leverage the deep learning technique to bridge the gap between traditional model-based methods and the requirement of reversing the blurry 2D barcode images. However, algorithms that use deep learning methods to deal with the blurring of QR code images are relatively rare, because the performance of deep learning models for deblurring QR code images in industrial automation still needs to be explored.…”

Section: Qr Code Image Deblurringmentioning

confidence: 99%

“…It adversely affects the decoding and the extraction of QR codes and leads to inaccurate representation of the information. In this regard, in view of the high-efficiency requirements of real-time systems, fast restoration plays a prominent role in many industrial applications such as merchandise flow systems, commodity production systems and package sorting systems [5].…”

mentioning

confidence: 99%