Dual-modal edible oil impurity dataset for weak feature detection
Abstract Edible oil may be mixed with tiny solid impurities like raw material fragments, hair, metal fragments and etc. during the production and manufacturing process. For food safety reasons, these tiny impurities need to be detected in the quality control process. As compared with manual detectio...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-024-04305-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850034968654249984 |
|---|---|
| author | Huiyu Wang Qianghua Chen Jianding Zhao Liwen Xu Ming Li Ying Zhao Qinpei Zhao Qin Lu |
| author_facet | Huiyu Wang Qianghua Chen Jianding Zhao Liwen Xu Ming Li Ying Zhao Qinpei Zhao Qin Lu |
| author_sort | Huiyu Wang |
| collection | DOAJ |
| description | Abstract Edible oil may be mixed with tiny solid impurities like raw material fragments, hair, metal fragments and etc. during the production and manufacturing process. For food safety reasons, these tiny impurities need to be detected in the quality control process. As compared with manual detection ways, computer vision-based impurity detection methods can greatly reduce the workload and improve the detection efficiency and accuracy. However, there are currently no datasets for the detection of solid impurities in edible oils. For this reason, a dual-modal edible oil impurity (DMEOI) dataset is developed and made publicly available. The dataset is composed of 14520 event and full-pic images and annotated in two ways. Five common edible oils and four typical impurities are included in the dataset. The DMEOI dataset can be used for liquid impurity detection in either single-modal or dual-modal way. To prove the usability of the dataset, four object detection algorithms are applied and compared. |
| format | Article |
| id | doaj-art-950ce31c027f4f869a39e548ff69b96e |
| institution | DOAJ |
| issn | 2052-4463 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Data |
| spelling | doaj-art-950ce31c027f4f869a39e548ff69b96e2025-08-20T02:57:39ZengNature PortfolioScientific Data2052-44632024-12-0111111110.1038/s41597-024-04305-wDual-modal edible oil impurity dataset for weak feature detectionHuiyu Wang0Qianghua Chen1Jianding Zhao2Liwen Xu3Ming Li4Ying Zhao5Qinpei Zhao6Qin Lu7School of Electronic Information, Shanghai Dianji UniversitySchool of Electronic Information, Shanghai Dianji UniversitySchool of Electronic Information, Shanghai Dianji UniversitySchool of Electronic Information, Shanghai Dianji UniversitySchool of Electronic Information, Shanghai Dianji UniversitySchool of Electronic Information, Shanghai Dianji UniversitySchool of Software Engineering, Tongji UniversityShanghai Jiaotong University School of MedicineAbstract Edible oil may be mixed with tiny solid impurities like raw material fragments, hair, metal fragments and etc. during the production and manufacturing process. For food safety reasons, these tiny impurities need to be detected in the quality control process. As compared with manual detection ways, computer vision-based impurity detection methods can greatly reduce the workload and improve the detection efficiency and accuracy. However, there are currently no datasets for the detection of solid impurities in edible oils. For this reason, a dual-modal edible oil impurity (DMEOI) dataset is developed and made publicly available. The dataset is composed of 14520 event and full-pic images and annotated in two ways. Five common edible oils and four typical impurities are included in the dataset. The DMEOI dataset can be used for liquid impurity detection in either single-modal or dual-modal way. To prove the usability of the dataset, four object detection algorithms are applied and compared.https://doi.org/10.1038/s41597-024-04305-w |
| spellingShingle | Huiyu Wang Qianghua Chen Jianding Zhao Liwen Xu Ming Li Ying Zhao Qinpei Zhao Qin Lu Dual-modal edible oil impurity dataset for weak feature detection Scientific Data |
| title | Dual-modal edible oil impurity dataset for weak feature detection |
| title_full | Dual-modal edible oil impurity dataset for weak feature detection |
| title_fullStr | Dual-modal edible oil impurity dataset for weak feature detection |
| title_full_unstemmed | Dual-modal edible oil impurity dataset for weak feature detection |
| title_short | Dual-modal edible oil impurity dataset for weak feature detection |
| title_sort | dual modal edible oil impurity dataset for weak feature detection |
| url | https://doi.org/10.1038/s41597-024-04305-w |
| work_keys_str_mv | AT huiyuwang dualmodaledibleoilimpuritydatasetforweakfeaturedetection AT qianghuachen dualmodaledibleoilimpuritydatasetforweakfeaturedetection AT jiandingzhao dualmodaledibleoilimpuritydatasetforweakfeaturedetection AT liwenxu dualmodaledibleoilimpuritydatasetforweakfeaturedetection AT mingli dualmodaledibleoilimpuritydatasetforweakfeaturedetection AT yingzhao dualmodaledibleoilimpuritydatasetforweakfeaturedetection AT qinpeizhao dualmodaledibleoilimpuritydatasetforweakfeaturedetection AT qinlu dualmodaledibleoilimpuritydatasetforweakfeaturedetection |