Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Automation and Machine Learning
  4. Vol 6, Issue 2, 2025

Review on Commodity Recognition and Inventory Counting Based on Machine Vision in Retail Scenarios

Download as PDF

DOI: 10.23977/autml.2025.060205 | Downloads: 4 | Views: 56

Author(s)

Ranning Deng 1

Affiliation(s)

1 School of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan, China

Corresponding Author

Ranning Deng

ABSTRACT

With the in-depth advancement of the digital transformation of the retail industry, machine vision technology has become a key support for optimizing the operational efficiency of supermarkets and convenience stores. This paper focuses on typical retail scenarios such as supermarkets and convenience stores, and systematically sorts out the application status of machine vision technology in three core links: commodity classification, shelf out-of-stock detection, and self-checkout recognition. It analyzes the technical characteristics of traditional manual feature extraction methods and modern deep learning methods in commodity recognition, and emphasizes the application value of the Grocery Dataset in algorithm training. Aiming at the key technical bottlenecks such as similar commodity packaging, stacked placement occlusion, and complex environmental interference, this paper summarizes the optimization strategies such as attention mechanism, multi-view fusion, and multi-modal combination, and discusses the practical experience of Retail Product Checkout (RPC) technology in complex shopping basket settlement scenarios. Finally, the paper analyzes the current challenges faced by unmanned retail in terms of environmental adaptability, computing power cost, and privacy protection, and puts forward development directions such as multi-technology integration, large-scale deployment, and human-machine collaboration. This review provides a comprehensive technical reference for the in-depth application of machine vision in the retail field. 

KEYWORDS

Machine Vision; Commodity Recognition; Inventory Counting; Retail Scenario; Unmanned Retail; Grocery Dataset; Retail Product Checkout

CITE THIS PAPER

Ranning Deng, Review on Commodity Recognition and Inventory Counting Based on Machine Vision in Retail Scenarios. Automation and Machine Learning (2025) Vol. 6: 38-42. DOI: http://dx.doi.org/10.23977/autml.2025.060205.

REFERENCES

[1] Redmon, Joseph, and Ali Farhadi. "Yolov3: An incremental improvement." arxiv preprint arxiv:1804.02767 (2018).
[2] Ren, Shaoqing, et al. "Faster R-CNN: Towards real-time object detection with region proposal networks." IEEE transactions on pattern analysis and machine intelligence 39.6 (2016): 1137-1149.
[3] Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems 30 (2017).
[4] Xizhou Zhu, et al. "Deformable detr: Deformable transformers for end-to-end object detection." arxiv preprint arxiv:2010.04159 (2020).
[5] Liu, Wei, et al. "Ssd: Single shot multibox detector." European conference on computer vision. Cham: Springer International Publishing, 2016.
[6] Howard, Andrew G., et al. "Mobilenets: Efficient convolutional neural networks for mobile vision applications." arxiv preprint arxiv:1704.04861 (2017).
[7] Qiu, Han, et al. "Borderdet: Border feature for dense object detection." European Conference on Computer Vision. Cham: Springer International Publishing, 2020.
[8] Chen, Kai, et al. "MMDetection: Open mmlab detection toolbox and benchmark." arxiv preprint arxiv:1906.07155 (2019).

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 4318
Visits: 199343

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.