Authentication of packed cigarettes based on computer vision and machine learning

ZHONG Yu1 XU Yan1 LIU Dexiang1 WANG Hongqiang1 LI Xiaohui2 ZHOU Mingzhu2 DONG Hao2 XING Jun2

(1.Xinjiang Tobacco Quality Test Station, Urumqi, China 830026)
(2.China National Tobacco Quality Supervision & Test Center, Zhengzhou, China 450001)

【Abstract】To pursue high efficiency and high accuracy in authentication of cigarette packets, an authentication model was established on the basis of computer vision and machine learning. Computer vision was adopted to process the images of cigarette packet and extract feature vectors and a similarity measurement model and a machine learning model were used separately to classify the feature vectors and to discriminate authentic and fake cigarettes. The similarity measurement model made classification with Manhattan distance and optimized the parameters in Gauss bilateral filter. Machine learning model was based on image segmentation, and determined the optimal amount and area of segment. A total of 603 samples of three cigarette brands, “CHUNGHWA”, “YUXI”, and “HEHUA”, were identified by the two models separately. The results showed that the accuracy of the similarity measurement model for the test set of brand “YUXI” was 96.17%, and the accuracies of the machine learning model for the test sets of brands “CHUNGHWA”, “YUXI”, and “HEHUA” reached 98.99%, 96.61%, and 100%, respectively. Compared with the similarity measurement model, the machine learning model has better migration ability and robustness and is suitable for the authentication of cigarette samples of large amount, multiple categories, and complex images. This method provides a technical support for improving the efficiency and accuracy of cigarette authentication.

【Keywords】 Cigarette packaging; Authentication; Computer vision; Machine learning; Similarity; Classification model;

【DOI】

【Funds】 Major Science and Technology Project of State Tobacco Monopoly Administration [110201901026(SJ-05)]

Download this article

    References

    [1] WEI Zhonghua. Method for cigarette authenticity discrimination based on t test and SVM neural network [J]. Tobacco Science & Technology, 2015, 48 (2): 75–78 (in Chinese).

    [2] NIE Lei, BIE Zhenying, ZHU You, et al. Non-destructive discrimination of genuine and fake cigarettes by attenuated total reflection infrared spectroscopy based on cigarette packaging materials [J]. Tobacco Science & Technology, 2019, 52 (5): 31–39 (in Chinese).

    [3] ZHANG Yi, WANG Yanbo, FU Huasen, et al. Irregular cigarette parcel stacking system coupled with machine vision-based parcel identification [J]. Tobacco Science & Technology, 2019, 52 (6): 105–111 (in Chinese).

    [4] GAO Zhenyu, WANG An, DONG Hao, et al. Identification of tobacco components in cut filler based on convolutional neural network [J]. Tobacco Science & Technology, 2017, 50 (9): 68–75 (in Chinese).

    [5] LI Xiao, ZHENG Liwen, HE Chao, et al. Morphology characterization of cut stem based on computer vision technology [J]. Tobacco Science & Technology, 2016, 49 (7): 84–90 (in Chinese).

    [6] LI Jie, LU Haihua, WANG Xiang, et al. Online cigarette appearance inspection system based on machine vision [J]. Tobacco Science & Technology, 2019, 52 (9): 109–114 (in Chinese).

    [7] WANG Wei, ZHU Liming, ZHANG Qiang, et al. Method for intelligent detection of carton missing in cigarette case based on similarity analysis and threshold self-correction [J]. Tobacco Science & Technology, 2019, 52 (1): 91–97 (in Chinese).

    [8] LIU Ze, LIN Wenqiang, ZHANG Yun, et al. Shape feature analysis of tobacco strips based on contour extraction [J]. Tobacco Science & Technology, 2018, 51 (4): 66–71 (in Chinese).

    [9] ZHANG Qing, XIA Yingwei, WANG Shu, et al. A method for measuring degree of square of cigarette packet based on computer vision [J]. Tobacco Science & Technology, 2017, 50 (11): 87–92 (in Chinese).

    [10] NIE Lixing, WANG Gangli, LI Zhimeng, et al. Application of near infrared spectroscopy in process analysis of TCM manufacturing [J]. Acta Optica Sinica, 2009, 29 (2): 541–547 (in Chinese).

    [11] Tan P N, Steinbach M, Kumar V. Introduction to data mining [M]. 2nd ed. FAN Ming, FAN Hongjian, trans. Beijing: Posts & Telecom Press, 2011 (in Chinese).

This Article

ISSN:1002-0861

CN:41-1137/TS

Vol 53, No. 05, Pages 83-92

May 2020

Downloads:8

Share
Article Outline

Knowledge

Abstract

  • 1 Materials and methods
  • 2 Results and discussion
  • 3 Conclusions
  • References