Classification of Cigarette Types Using Computer Vision: An Analysis of Smoke Aggregation Features
The aggregation of cigarette smoke is one of the key indicators when consumers taste cigarettes. The purpose of this study is to explore the characteristics of smoke images through computer vision technology, and distinguish different brands of cigarettes by using the aggregation characteristics of...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10771730/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590326384033792 |
|---|---|
| author | Shishuan Guan Lei Jiao Zengyu Wang Xiaofei Ji Hongwei Zheng Cunfeng Yu Hongtao Li Liwen Zheng Shuaishuai Sun Qiang Sun Jun Li Guangwei Jiang Kezhi Wu Erge Lin Xinlong Zhang |
| author_facet | Shishuan Guan Lei Jiao Zengyu Wang Xiaofei Ji Hongwei Zheng Cunfeng Yu Hongtao Li Liwen Zheng Shuaishuai Sun Qiang Sun Jun Li Guangwei Jiang Kezhi Wu Erge Lin Xinlong Zhang |
| author_sort | Shishuan Guan |
| collection | DOAJ |
| description | The aggregation of cigarette smoke is one of the key indicators when consumers taste cigarettes. The purpose of this study is to explore the characteristics of smoke images through computer vision technology, and distinguish different brands of cigarettes by using the aggregation characteristics of smoke, hoping to provide preliminary support for automatic cigarette identification. Firstly, we constructed a 3D model experimental platform based on the human upper respiratory tract to create the cigarette smoke image dataset SmogAg. This data set contains sequence image data of smoke movement patterns of 51 types of cigarettes, including thick, medium and thin cigarettes. Based on this data set, we applied the traditional vision algorithm to extract the diffusion width, sedimentation concentration and diffusion distance of smoke, and used the KNN model for training, and initially reached an accuracy of 69.8%. To further improve performance, we have adopted a new network architecture. We first adopted SmokeSeqNet model for experiments, which combined residual CNN as a feature extractor and captured the dynamic sequence characteristics of smoke through the LSTM layer. This method, combined with time series analysis, not only improved the accuracy, but also gave us insight into the time-dependent behavior of the smoke, ultimately achieving an accuracy of 81.6%. In order to further improve the performance, we build SmokeSeqNetV2 model to continue the experiment, which introduces Swin-Transformer feature extraction module and attention mechanism, and the final accuracy rate reaches 88.9%. Through computer vision technology, we began to explore the image characteristics of smoke, hoping to provide a new idea for distinguishing different brands of cigarettes by the aggregation characteristics of smoke. |
| format | Article |
| id | doaj-art-5214f4c0b35a4755832598e66f8c7e5e |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-5214f4c0b35a4755832598e66f8c7e5e2025-01-24T00:01:21ZengIEEEIEEE Access2169-35362025-01-0113118361184510.1109/ACCESS.2024.350874810771730Classification of Cigarette Types Using Computer Vision: An Analysis of Smoke Aggregation FeaturesShishuan Guan0Lei Jiao1Zengyu Wang2Xiaofei Ji3Hongwei Zheng4Cunfeng Yu5Hongtao Li6Liwen Zheng7Shuaishuai Sun8Qiang Sun9Jun Li10Guangwei Jiang11Kezhi Wu12Erge Lin13Xinlong Zhang14Shandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaQingdao University, Qingdao, Shandong, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaShandong Qingdao Tobacco Company Ltd., Laoshan, Qingdao, ChinaThe aggregation of cigarette smoke is one of the key indicators when consumers taste cigarettes. The purpose of this study is to explore the characteristics of smoke images through computer vision technology, and distinguish different brands of cigarettes by using the aggregation characteristics of smoke, hoping to provide preliminary support for automatic cigarette identification. Firstly, we constructed a 3D model experimental platform based on the human upper respiratory tract to create the cigarette smoke image dataset SmogAg. This data set contains sequence image data of smoke movement patterns of 51 types of cigarettes, including thick, medium and thin cigarettes. Based on this data set, we applied the traditional vision algorithm to extract the diffusion width, sedimentation concentration and diffusion distance of smoke, and used the KNN model for training, and initially reached an accuracy of 69.8%. To further improve performance, we have adopted a new network architecture. We first adopted SmokeSeqNet model for experiments, which combined residual CNN as a feature extractor and captured the dynamic sequence characteristics of smoke through the LSTM layer. This method, combined with time series analysis, not only improved the accuracy, but also gave us insight into the time-dependent behavior of the smoke, ultimately achieving an accuracy of 81.6%. In order to further improve the performance, we build SmokeSeqNetV2 model to continue the experiment, which introduces Swin-Transformer feature extraction module and attention mechanism, and the final accuracy rate reaches 88.9%. Through computer vision technology, we began to explore the image characteristics of smoke, hoping to provide a new idea for distinguishing different brands of cigarettes by the aggregation characteristics of smoke.https://ieeexplore.ieee.org/document/10771730/Smoke aggregationcomputer visionresidual CNN+LSTMSwin-Transformerattention mechanism |
| spellingShingle | Shishuan Guan Lei Jiao Zengyu Wang Xiaofei Ji Hongwei Zheng Cunfeng Yu Hongtao Li Liwen Zheng Shuaishuai Sun Qiang Sun Jun Li Guangwei Jiang Kezhi Wu Erge Lin Xinlong Zhang Classification of Cigarette Types Using Computer Vision: An Analysis of Smoke Aggregation Features IEEE Access Smoke aggregation computer vision residual CNN+LSTM Swin-Transformer attention mechanism |
| title | Classification of Cigarette Types Using Computer Vision: An Analysis of Smoke Aggregation Features |
| title_full | Classification of Cigarette Types Using Computer Vision: An Analysis of Smoke Aggregation Features |
| title_fullStr | Classification of Cigarette Types Using Computer Vision: An Analysis of Smoke Aggregation Features |
| title_full_unstemmed | Classification of Cigarette Types Using Computer Vision: An Analysis of Smoke Aggregation Features |
| title_short | Classification of Cigarette Types Using Computer Vision: An Analysis of Smoke Aggregation Features |
| title_sort | classification of cigarette types using computer vision an analysis of smoke aggregation features |
| topic | Smoke aggregation computer vision residual CNN+LSTM Swin-Transformer attention mechanism |
| url | https://ieeexplore.ieee.org/document/10771730/ |
| work_keys_str_mv | AT shishuanguan classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT leijiao classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT zengyuwang classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT xiaofeiji classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT hongweizheng classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT cunfengyu classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT hongtaoli classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT liwenzheng classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT shuaishuaisun classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT qiangsun classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT junli classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT guangweijiang classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT kezhiwu classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT ergelin classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures AT xinlongzhang classificationofcigarettetypesusingcomputervisionananalysisofsmokeaggregationfeatures |