{"id":6877,"date":"2026-05-17T22:49:47","date_gmt":"2026-05-17T14:49:47","guid":{"rendered":"\/jase\/?post_type=tkuisotope&p=6877"},"modified":"2026-05-27T20:20:43","modified_gmt":"2026-05-27T12:20:43","slug":"jase-202609-32-037","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=jase-202609-32-037","title":{"rendered":"Automatic recognition and classification of product packaging images based on convolutional neural network"},"content":{"rendered":"\n
\n
\n

<\/i> 2026<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 32<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

You Li1<\/sup> and Chen Jiang2<\/sup><\/i><\/a> <\/p>\n\n\n\n

1College of Art and Design, Wuhan Technology and Business University, Wuhan, Hubei 430065, China<\/p>\n\n\n\n

2<\/sup>School of art and media, Wuhan College, Wuhan, Hubei 430065, China<\/p>\n<\/div>\n\n\n\n

\n

Received: February 12, 2026
Accepted: April 4, 2026
Publication Date: May 17, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

Overall architecture of MSAFNet. The framework integrates a hybrid backbone network, attention modules, and a multi-scale feature pyramid to improve feature extraction and object detection performance for product packaging images. <\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/i> Copyright <\/strong>The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0)<\/a>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.<\/p>\n\n\n\n

Download Citation:  BibTeX <\/a>| http:\/\/dx.doi.org\/10.6180\/jase.202609_32.037<\/a>  <\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

Traditional packaging image recognition methods rely on manual detection or manual feature extraction, which has the problems of low efficiency and poor adaptability, while existing deep learning models still face challenges when dealing with complex backgrounds, small target detection, and category imbalance. The purpose of this paper is to design an efficient and reliable product packaging image recognition system. By proposing a multi-scale attention fusion network (MSAFNet), this paper integrates a lightweight hybrid backbone network (combined with EfficientNet and ResNet), a dual attention module (DAM) to enhance feature focusing, an adaptive multi-scale feature pyramid (AFPN) to optimize multi-scale fusion, and a multi-task learning framework to jointly optimize detection and classification. The proposed model achieves an mAP@0.5 of 89.6% on the COCO dataset, outperforming the baseline by 4.4% while maintaining real-time performance at 40 FPS with only 8.9 M parameters. It demonstrates strong robustness with a low performance degradation rate of 10.8% and good generalization with only 6.1% cross-dataset degradation. These results highlight its effectiveness in balancing accuracy, efficiency, and scalability for industrial applications. The architecture design and system validation confirm its suitability for automated packaging detection tasks. However, performance under extreme occlusion remains a limitation and can be improved through future self-supervised learning approaches.<\/p>\n\n\n\n

Keywords: convolutional neural network; products; packaging images; automatic identification; classification<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
\n
\n
    \n
  1. [1] S. Y. Chaganti, I. Nanda, K. R. Pandi, T. G. Prudhvith, and N. Kumar, (2020) \u201cImage classification using SVM and CNN\u201d Proceedings of the 2020 International Conference on Computer Science, Engineering and Applications (ICCSEA): 1\u20135. DOI: 10.1109\/ICCSEA49143.2020.9132851.<\/li>\n
  2. [2] Z. Liu, L. Sun, and Q. Zhang, (2022) \u201cHigh similarity image recognition and classification algorithm based on convolutional neural network\u201d Computational Intelligence and Neuroscience 2022: 2836486. DOI: 10.1155\/2022\/2836486.<\/li>\n
  3. [3] K. V. Greeshma and J. V. Gripsy, (2020) \u201cImage classification using HOG and LBP feature descriptors with SVM and CNN\u201d International Journal of Engineering Research and Technology 8(4): 1\u20134. URL: https:\/\/d1wqtxts1xzle7.cloudfront.net\/110347554<\/a>.<\/li>\n
  4. [4] M. Z. Alom, M. Hasan, C. Yakopcic, T. M. Taha, and V. K. Asari, (2020) \u201cImproved inception-residual convolutional neural network for object recognition\u201d Neural Computing and Applications 32(1): 279\u2013293. DOI: 10.1007\/s00521-018-3627-6.<\/li>\n
  5. [5] T. Hassanzadeh, D. Essam, and R. Sarker, (2022) \u201cEvoDCNN: An evolutionary deep convolutional neural network for image classification\u201d Neurocomputing 488: 271\u2013283. DOI: 10.1016\/j.neucom.2022.02.003.<\/li>\n
  6. [6] M. Tripathi, (2021) \u201cAnalysis of convolutional neural network-based image classification techniques\u201d Journal of Innovative Image Processing 3(2): 100\u2013117. DOI: 10.36548\/jiip.2021.2.003.<\/li>\n
  7. [7] M. A. Hasan, T. Bhargav, V. Sandeep, V. S. Reddy, and R. Ajay, (2024) \u201cImage classification using convolutional neural networks\u201d International Journal of Mechanical Engineering Research and Technology 16(2): 173\u2013181. DOI: 10.1109\/ICEEICT53079.2022.9768622.<\/li>\n
  8. [8] M. Yang, P. Kumar, J. Bhola, and M. Shabaz, (2022) \u201cDevelopment of image recognition software based on artificial intelligence algorithm for the efficient sorting of apple fruit\u201d International Journal of System Assurance Engineering and Management 13(Suppl. 1): 322\u2013330. DOI: 10.1007\/s13198-021-01415-1.<\/li>\n
  9. [9] Z. Ren, F. Fang, N. Yan, and Y. Wu, (2022) \u201cState of the art in defect detection based on machine vision\u201d International Journal of Precision Engineering and Manufacturing\u2013Green Technology 9(2): 661\u2013691. DOI: 10.1007\/s40684-021-00343-6.<\/li>\n
  10. [10] Y. Liu, H. Pu, and D. W. Sun, (2021) \u201cEfficient extraction of deep image features using convolutional neural network (CNN) for applications in detecting and analysing complex food matrices\u201d Trends in Food Science and Technology 113: 193\u2013204. DOI: 10.1016\/j.tifs.2021.04.042.<\/li>\n
  11. [11] Q. Zhang, Q. Yang, X. Zhang, Q. Bao, J. Su, and X. Liu, (2021) \u201cWaste image classification based on transfer learning and convolutional neural network\u201d Waste Management 135: 150\u2013157. DOI: 10.1016\/j.wasman.2021.08.038.<\/li>\n
  12. [12] K. U. S. W. O. R. O. Adi, C. E. Widodo, A. P. Widodo, and U. S. Margiati, (2022) \u201cDetection of foreign object debris (FOD) using convolutional neural network (CNN)\u201d Journal of Theoretical and Applied Information Technology 100(1): 184\u2013191. URL: https:\/\/www.jatit.org\/volumes\/Vol100No1\/16Vol100No1.pdf<\/a>.<\/li>\n
  13. [13] S. Masood, U. Ahsan, F. Munawwar, D. R. Rizvi, and M. Ahmed, (2020) \u201cScene recognition from image using convolutional neural network\u201d Procedia Computer Science 167: 1005\u20131012. DOI: 10.1016\/j.procs.2020.03.400.<\/li>\n
  14. [14] Y. Li, R. G. Zhou, R. Xu, J. Luo, and W. Hu, (2020) \u201cA quantum deep convolutional neural network for image recognition\u201d Quantum Science and Technology 5(4): 044003. DOI: 10.1088\/2058-9565\/ab9f93.<\/li>\n
  15. [15] G. Chen, Q. Chen, S. Long, W. Zhu, Z. Yuan, and Y. Wu, (2023) \u201cQuantum convolutional neural network for image classification\u201d Pattern Analysis and Applications 26(2): 655\u2013667. DOI: 10.1007\/s10044-022-01113-z.<\/li>\n
  16. [16] R. Basha, P. Pathak, M. Sudha, K. V. Soumya, and J. Arockia Venice, (2025) \u201cOptimization of quantum dilated convolutional neural networks: Image recognition with quantum computing\u201d Internet Technology Letters 8(3): e70027. DOI: 10.1002\/itl2.70027.<\/li>\n
  17. [17] H. C. V. Ngu and K. M. Lee, (2022) \u201cEffective conversion of a convolutional neural network into a spiking neural network for image recognition tasks\u201d Applied Sciences 12(11): 5749. DOI: 10.3390\/app12115749.<\/li>\n
  18. [18] V. Guizilini, R. Ambrus, S. Pillai, A. Raventos, and A. Gaidon, (2020) \u201c3D packing for self-supervised monocular depth estimation\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition: 2485\u20132494. URL: https:\/\/openaccess.thecvf.com\/content_CVPR_2020\/html\/Guizilini_3D_Packing_for_Self-Supervised_Monocular_Depth_Estimation_CVPR_2020_paper.html<\/a>. <\/span><\/li>\n
  19. [19] I. J. Jacob and P. E. Darney, (2021) \u201cDesign of deep learning algorithm for IoT application by image-based recognition\u201d Journal of ISMAC 3(3): 276\u2013290. DOI: 10.36548\/jismac.2021.3.008. <\/span><\/li>\n
  20. [20] C. Zhang, M. Han, J. Jia, and C. Kim, (2024) \u201cPackaging design image segmentation based on improved full convolutional networks\u201d Applied Sciences 14(22): 10742. DOI: 10.3390\/app142210742. <\/span><\/li>\n
  21. [21] S. Aburass, A. Huneiti, and M. B. Al-Zoubi, (2022) \u201cClassification of transformed and geometrically distorted images using convolutional neural network\u201d Journal of Computer Science 18(8): 757\u2013769. DOI: 10.3844\/jcssp.2022.757.769. <\/span><\/li>\n
  22. [22] D. Dai, Y. Li, Y. Wang, H. Bao, and G. Wang, (2022) \u201cRethinking the image feature biases exhibited by deep convolutional neural network models in image recognition\u201d CAAI Transactions on Intelligence Technology 7(4): 721\u2013731. DOI: 10.1049\/cit2.12097. <\/span><\/li>\n
  23. [23] M. Nauta, R. Van Bree, and C. Seifert, (2021) \u201cNeural prototype trees for interpretable fine-grained image recognition\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition: 14933\u201314943. URL: <\/span>https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/html\/Nauta_Neural_Prototype_Trees_for_Interpretable_Fine-Grained_Image_Recognition_CVPR_2021_paper.html<\/a>. <\/span><\/li>\n
  24. [24] Q. Cao, (2021) \u201cThe art of packaging: an investigation on modern packaging design and artistic thinking under the background of big data\u201d Journal of Applied Science and Engineering 24(4): 807\u2013812. DOI: 10.6180\/jase.202110_24(5).0017.<\/span><\/li>\n<\/ol>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[12,720,6],"tags":[1446],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. Download Citation:  BibTeX | http:\/\/dx.doi.org\/10.6180\/jase.202609_32.037   Download PDF Traditional packaging image recognition methods rely on manual detection or manual…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/6877"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6877"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6877"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6877"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}