|
二维码（扫一下试试看！） |
| Study on Quality Evaluation Method of Cigarette Trademark Paper Based on Machine Vision and Deep Learning |
| Received:April 30, 2025 Revised:June 09, 2025 |
| DOI：10.11980/j.issn.0254-508X.2025.11.026 |
| Key Words:machine vision deep learning YOLOv8 cigarette trademark paper quality inspection similarity computation |
| Fund Project:上海烟草集团有限责任公司科技项目（K2023-1-024P）。 |
| Author Name | Affiliation | Postcode | | WANG Lyu* | Shanghai Tobacco Group Co., Ltd., Shanghai,200082 | 200082 | | CAO Changqing | Shanghai Tobacco Group Co., Ltd., Shanghai,200082 | 200082 | | SI Yong | Shanghai Tobacco Group Co., Ltd., Shanghai,200082 | 200082 | | SHEN Qiang | Shanghai Chuangheyi Electronic Technology Development Co., Ltd., Shanghai,200090 | 200090 | | DING Ran | Shanghai Tobacco Group Co., Ltd., Shanghai,200082 | 200082 | | LIN Sen | Shanghai Tobacco Group Co., Ltd., Shanghai,200082 | 200082 | | SHEN Zhiyan | Shanghai Tobacco Group Co., Ltd., Shanghai,200082 | 200082 | | XUE Chen | Shanghai Chuangheyi Electronic Technology Development Co., Ltd., Shanghai,200090 | 200090 | | XIA Zhicheng | Shanghai Tobacco Group Co., Ltd., Shanghai,200082 | 200082 | | CHEN Renyu | Shanghai Tobacco Group Co., Ltd., Shanghai,200082 | 200082 | | XU Yanmin | Shanghai Tobacco Group Co., Ltd., Shanghai,200082 | 200082 | | ZHANG Jun | Shanghai Tobacco Group Co., Ltd., Shanghai,200082 | 200082 | | PENG Yunfa | Shanghai Chuangheyi Electronic Technology Development Co., Ltd., Shanghai,200090 | 200090 | | ZHAN Ying* | Shanghai Chuangheyi Electronic Technology Development Co., Ltd., Shanghai,200090 | 200090 |
|
| Hits: 2075 |
| Download times: 760 |
| Abstract:To investigate the application of machine vision technology integrating deep learning in evaluating the quality inspection results of cigarette trademark paper，this study proposed a comprehensive evaluation method. A high-resolution industrial camera， customized light sources， and specialized software systems were employed to construct an annotated dataset. Dynamic threshold ORB feature detection， optimized RANSAC registration， and multi-band fusion strategies were adopted， effectively eliminating stitching seams. The images PSNR of 38.9 dB and SSIM of 0.94. For feature recognition， the YOLOv8 model was enhanced by introducing a CBAM attention module， combined with a ResNet-34 backbone network and FPN multi-scale feature fusion， achieving 99.4% mAP50， 99.6% recall， and 99.0% precision on the test set. A dual-branch Siamese network was designed to compute similarity by fusing SIFT descriptors and deep semantic features， achieving average recognition accuracies of 97.64% for small box trademark paper and 95.85% for carton trademark paper. |
| View Full Text HTML View/Add Comment Download reader |
|
|
|