Identification method of canned food for production line sorting robot based on improved PSO-SVM
<b>Objective:</b> To solve the problems of poor accuracy and low efficiency in target recognition methods for existing sorting robots in food production lines. <b>Methods:</b> On the basis of the analysis of the binocular vision food sorting system, a combination of improved...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Editorial Office of Food and Machinery
2023-10-01
|
| Series: | Shipin yu jixie |
| Subjects: | |
| Online Access: | http://www.ifoodmm.com/spyjxen/article/abstract/20230915 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850159465871966208 |
|---|---|
| author | GAO Haiyan GAO Jinyang WANG Weicheng |
| author_facet | GAO Haiyan GAO Jinyang WANG Weicheng |
| author_sort | GAO Haiyan |
| collection | DOAJ |
| description | <b>Objective:</b> To solve the problems of poor accuracy and low efficiency in target recognition methods for existing sorting robots in food production lines. <b>Methods:</b> On the basis of the analysis of the binocular vision food sorting system, a combination of improved particle swarm optimization algorithm and support vector machine was proposed for target recognition of food sorting robots. By improving the particle swarm optimization algorithm to optimize support vector machine parameters, an optimized support vector machine classification model was obtained. The classifier was trained for both global and local features, and feature weight coefficients were dynamically assigned to obtain the best recognition rate. Analyzed the performance of the proposed method through experiments, and verified its feasibility. <b>Results:</b> Compared with conventional methods, the proposed method had high recognition accuracy and efficiency in target recognition of food sorting robots, with an accuracy rate of 99.50% and an average recognition time of 0.048 s, which meet the needs of robot sorting. <b>Conclusion:</b> The proposed method can effectively identify canning, improved sorting accuracy and efficiency of sorting robots. |
| format | Article |
| id | doaj-art-8b491462189e485784eac102350cf7ec |
| institution | OA Journals |
| issn | 1003-5788 |
| language | English |
| publishDate | 2023-10-01 |
| publisher | The Editorial Office of Food and Machinery |
| record_format | Article |
| series | Shipin yu jixie |
| spelling | doaj-art-8b491462189e485784eac102350cf7ec2025-08-20T02:23:31ZengThe Editorial Office of Food and MachineryShipin yu jixie1003-57882023-10-01399899410.13652/j.spjx.1003.5788.2023.60066Identification method of canned food for production line sorting robot based on improved PSO-SVMGAO Haiyan0GAO Jinyang1WANG Weicheng2 Jinzhong Vocational & Technical College, Jinzhong, Shanxi 030600 , China North University of China, Taiyuan, Shanxi 030051 , China Shanxi Agricultural University, Taiyuan, Shanxi 030031 , China <b>Objective:</b> To solve the problems of poor accuracy and low efficiency in target recognition methods for existing sorting robots in food production lines. <b>Methods:</b> On the basis of the analysis of the binocular vision food sorting system, a combination of improved particle swarm optimization algorithm and support vector machine was proposed for target recognition of food sorting robots. By improving the particle swarm optimization algorithm to optimize support vector machine parameters, an optimized support vector machine classification model was obtained. The classifier was trained for both global and local features, and feature weight coefficients were dynamically assigned to obtain the best recognition rate. Analyzed the performance of the proposed method through experiments, and verified its feasibility. <b>Results:</b> Compared with conventional methods, the proposed method had high recognition accuracy and efficiency in target recognition of food sorting robots, with an accuracy rate of 99.50% and an average recognition time of 0.048 s, which meet the needs of robot sorting. <b>Conclusion:</b> The proposed method can effectively identify canning, improved sorting accuracy and efficiency of sorting robots.http://www.ifoodmm.com/spyjxen/article/abstract/20230915 food production line sorting robot target recognition particle swarm optimization algorithm support vector machine |
| spellingShingle | GAO Haiyan GAO Jinyang WANG Weicheng Identification method of canned food for production line sorting robot based on improved PSO-SVM Shipin yu jixie food production line sorting robot target recognition particle swarm optimization algorithm support vector machine |
| title | Identification method of canned food for production line sorting robot based on improved PSO-SVM |
| title_full | Identification method of canned food for production line sorting robot based on improved PSO-SVM |
| title_fullStr | Identification method of canned food for production line sorting robot based on improved PSO-SVM |
| title_full_unstemmed | Identification method of canned food for production line sorting robot based on improved PSO-SVM |
| title_short | Identification method of canned food for production line sorting robot based on improved PSO-SVM |
| title_sort | identification method of canned food for production line sorting robot based on improved pso svm |
| topic | food production line sorting robot target recognition particle swarm optimization algorithm support vector machine |
| url | http://www.ifoodmm.com/spyjxen/article/abstract/20230915 |
| work_keys_str_mv | AT gaohaiyan identificationmethodofcannedfoodforproductionlinesortingrobotbasedonimprovedpsosvm AT gaojinyang identificationmethodofcannedfoodforproductionlinesortingrobotbasedonimprovedpsosvm AT wangweicheng identificationmethodofcannedfoodforproductionlinesortingrobotbasedonimprovedpsosvm |