Full vector intelligent detection of cigarette appearance based on machine vision

Shifei Jiang; Zhaoguo Zhang; Faan Wang; Zhi Li; Kaiting Xie; Chenglin Wang; Jinhao Liang

Open Journal Systems

Full vector intelligent detection of cigarette appearance based on machine vision

Shifei Jiang, Zhaoguo Zhang, Faan Wang, Zhi Li, Kaiting Xie, Chenglin Wang, Jinhao Liang

Abstract

As the final output product of tobacco agriculture, the appearance quality of cigarettes is the key link to control. However, there is no special detection equipment for the whole appearance defect detection of tobacco, while it mainly depends on manual detection, leading to the test standard is not unique and the test data cannot be stored effectively. In this research, the shape characteristics and appearance inspection requirements of cigarettes were analyzed with the black-box method. Then, a kind of cigarette appearance quality inspection equipment was designed, and the experimental data of the equipment was analyzed with Design-Expert11. The results show that the device can image the appearance of a cigarette completely. The optimum parameters of the equipment are: the lifting speed of slide plate is 0.3 m/s, the angle of transition plate is 40°, the displacement speed of roller is 0.045 m/s, the movement speed of the slide plate is 0.4 m/s, the expansion speed of the cylinder is 20 mm/s, the spring coefficient is 3 n/s, the angle of the light source is 10°, and the height difference between the light source and the cigarette is 30 mm. The equipment can meet the needs of cigarette appearance detection and provide a reference for cylindrical object appearance detection.

Keywords

visual detection; cigarette appearance; full vector detection; convolutional neural network; cylindrical object detection

Full Text:

PDF

References

1. Phiri J, Malec K, Majune SK, et al. Durability of Zambia’s agricultural exports. Agriculture 2021; 11(1): 73. doi: 10.3390/agriculture11010073

2. Akhtar MN, Ansari E, Alhady SSN, et al. Leveraging on advanced remote sensing- and artificial intelligence-based technologies to manage palm oil plantation for current global scenario: A review. Agriculture. 2023; 13(2): 504. doi: 10.3390/agriculture13020504

3. Xiong Y, Li Y, Wang C, et al. Non-destructive detection of chicken freshness based on electronic nose technology and transfer learning. Agriculture 2023; 13(2): 496. doi: 10.3390/agriculture13020496

4. Wang X, Zhi M. Summary of object detection based on convolutional neural network. In: Proceedings of the Eventh International Conference on Graphics and Image Processing (ICGIP 2019); 12–14 October 2019; Hangzhou, China.

5. Ma D, Tang P, Zhao L. Review of data augmentation for image in deep learning. Journal of Image and Graphics 2021; 26(3): 487–502.

6. Ren Z, Fang F, Yan N, et al. State of the art in defect detection based on machine vision. International Journal of Precision Engineering and Manufacturing-Green Technology 2021; 9(2): 661–691. doi: 10.1007/s40684-021-00343-6

7. Lee PJ, Bui TA, Yao SR. Improve the HEVC algorithm complexity based on the visual perception. In: Proceedings of the 2019 IEEE International Conference on Consumer Electronics (ICCE); 11–13 January 2019; Las Vegas, NV, USA. pp. 1–4, doi: 10.1109/ICCE.2019.8662038

8. Jin Z, Zhong F, Zhang Q, et al. Visual detection of tobacco packaging film based on apparent features. International Journal of Advanced Robotic Systems 2021; 18(3): 172988142110248. doi: 10.1177/17298814211024839

9. Hu Y, Luo X, Gao Z, et al. Curve skeleton extraction from incomplete point clouds of livestock and its application in posture evaluation. Agriculture 2022; 12(7): 998. doi: 10.3390/agriculture12070998

10. Yu JJ, Zhou J, Xue R. Weld surface quality detection based on structured light and illumination model. Chinese Journal of Lasers 2022; 49(16): 170–178.

11. Tian X, Wang Z, Wang JX. Text detection of food labels based on semantic segmentation. Transactions of the Chinese Society for Agricultural Machinery 2020; 51(08): 336–343.

12. Zhao B. Research on the Key Technology of Drug Packaging Detection Based on Machine Vision. Liaoning University of Technology; 2022.

13. Xiao C, Qiu H. A count measurement method for low contrast stacked sheets in machine vision. Journal of Hunan University (National Science) 2018; 45(4): 122–128.

14. Madessa AH, Dong J, Dong X, et al. Leveraging an instance segmentation method for detection of transparent materials. In: Proceedings of the 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI); 19–23 August 2019; Leicester, UK. pp. 406–412. doi: 10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00113

15. Liu J, Dong L, Suo X. Study on visual detection of foreign matter in groove of zirconium tube based on average template method. Journal of Hunan University (National Science) 2020; 44(12): 53–60.

16. Deng Y, Pu H, Hua X, Sun B. Research on lane detection based on RC-DBSCAN. Journal of Hunan University (National Science) 2021; 48(10): 85–92.

17. Chen X, Fang Y, Du S, et al. Rapid packaging defect detection method based on deep learning. Machine Design and Research 2021; 37(06): 165–169.

18. Hou B, Hu Y, Zhang P, et al. Potato late blight severity and epidemic period prediction based on Vis/NIR spectroscopy. Agriculture 2022; 12(7): 897. doi: 10.3390/agriculture12070897

19. Zhang Z, Zhang Z, Li J. Potato detection in complex environment based on improved YoloV4 model. Transactions of the Chinese Society of Agricultural Engineering 2021; 37(22): 170–178.

20. Jiang T, Zhang G, Gao J. Illumination of a cylinder block transverse hole for machine vision inspection. Chinese Optics 2020; 12(06): 1285–1292.

21. Xu J. Research on Visual Inspection Algorithm for Label Defect of Cylindrical Products. Guangzhou University; 2018.

22. Liu R. Design and Implementation of Full-Appearance Visual Inspection System for Rotary Parts. Shanghai University of Engineering Science; 2021.

23. Liu Z. Application of black box method in fault detection of tunneling electrical control system. Mechanical & Electrical Engineering Technology 2019; 48(12): 233–235.

24. Jiang D. A brief analysis of Yolov3 and Yolov4. Available online: https://zhuanlan.zhihu.com/p/143747 (accessed on 19 December 2021).

25. Wang W, Wang H, Dong Z. Deep learning data augmentation method in microscopy imaging. Laser Journal 2022; 43(2): 96–100.

26. Wang J, Chen X, Yang Z. Influence of different data augmentatio methods on model recognition accuracy. Computer Science 2019; 48(12): 233–235.

27. Fan D, Sun X, Wang Q. Multistage dense block hourglass network for human pose estimation. Transducer and Microsystem Technologies 2020; 39(11): 47–52.

(31 Abstract Views, 21 PDF Downloads)