Article: Lightweight QR code detection network for digital tracking of cigar sales Journal: International Journal of Intelligent Information and Database Systems (IJIIDS) 2026 Vol.18 No.3/4 pp.369 - 389 Abstract: In response to the prevalence of illicit cigarettes in the market, the development of digital tracking systems becomes imperative to combat cigar smuggling. However, the formidable challenge of inspecting cigars hampers the creation of an effective QR code tracking system. In this regard, we propose a lightweight QR code detection network to trace the trajectory of each cigar. The proposed detection model employs YoLoV5 network as its backbone, and changes the convolutional layers to depthwise separable convolutions and lightweight processes the residual modules. To ensure the learning ability of the proposed lightweight network, we draw on the idea of knowledge distillation, that is, the original YoLoV5 network is used as the teacher model to guide the training of the lightweight YoLoV5 (LW YoLoV5) model. Finally, the network slimming technology is introduced to prune the trained network, in order to further reduce the number of model parameters and accelerate the inference speed of the model. Experimental results demonstrate that the proposed lightweight model can swiftly and accurately detect QR codes, surpassing other algorithms in comparative evaluations. Inderscience Publishers - linking academia, business and industry through research

Title: Lightweight QR code detection network for digital tracking of cigar sales

Authors: Rui Sun; Wenguang Ma; Xianghua Li; Shihua He; Degang Zhang; Zhaozhen Zhang

Addresses: Yunnan Tobacco Company Lijiang City Company, Lijiang, 674100, Yunnan, China ' Yunnan Tobacco Company Lijiang City Company, Lijiang, 674100, Yunnan, China ' Yunnan Tobacco Company Lijiang City Company, Lijiang, 674100, Yunnan, China ' Yunnan Tobacco Company Lijiang City Company, Lijiang, 674100, Yunnan, China ' Yunnan Tobacco Company Lijiang City Company, Lijiang, 674100, Yunnan, China ' Yunnan Tobacco Company Lijiang City Company, Lijiang, 674100, Yunnan, China

Abstract: In response to the prevalence of illicit cigarettes in the market, the development of digital tracking systems becomes imperative to combat cigar smuggling. However, the formidable challenge of inspecting cigars hampers the creation of an effective QR code tracking system. In this regard, we propose a lightweight QR code detection network to trace the trajectory of each cigar. The proposed detection model employs YoLoV5 network as its backbone, and changes the convolutional layers to depthwise separable convolutions and lightweight processes the residual modules. To ensure the learning ability of the proposed lightweight network, we draw on the idea of knowledge distillation, that is, the original YoLoV5 network is used as the teacher model to guide the training of the lightweight YoLoV5 (LW YoLoV5) model. Finally, the network slimming technology is introduced to prune the trained network, in order to further reduce the number of model parameters and accelerate the inference speed of the model. Experimental results demonstrate that the proposed lightweight model can swiftly and accurately detect QR codes, surpassing other algorithms in comparative evaluations.

Keywords: lightweight network; QR code detection; cigar sales; digital tracking.

DOI: 10.1504/IJIIDS.2026.155314

International Journal of Intelligent Information and Database Systems, 2026 Vol.18 No.3/4, pp.369 - 389

Received: 25 Jan 2024
Accepted: 07 May 2024
Published online: 30 Jul 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Lightweight QR code detection network for digital tracking of cigar sales

Keep up-to-date