Pill Recognition via Deep Learning Approaches
Deep learning significantly transforms pill imaging recognition in the healthcare and pharmaceutical industries by automating the identification and classification processes based on visual indicators. It is important to develop a robust deep learning framework to ensure the accurate dispensing of m...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit UMP
2024
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/43006/ http://umpir.ump.edu.my/id/eprint/43006/1/Pill%20Recognition%20via%20Deep%20Learning%20Approaches.pdf |
| _version_ | 1848826756664918016 |
|---|---|
| author | Mohd Rais Hakim, Ramlee Ismail, Mohd Khairuddin Zubaidah, Zamri Muhammad Nur Aiman, Shapiee Muhammad Amirul, Abdullah |
| author_facet | Mohd Rais Hakim, Ramlee Ismail, Mohd Khairuddin Zubaidah, Zamri Muhammad Nur Aiman, Shapiee Muhammad Amirul, Abdullah |
| author_sort | Mohd Rais Hakim, Ramlee |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Deep learning significantly transforms pill imaging recognition in the healthcare and pharmaceutical industries by automating the identification and classification processes based on visual indicators. It is important to develop a robust deep learning framework to ensure the accurate dispensing of medications. The features such as size, color, shape, markings and text imprint are scrutinized by these methods. However, real-world matching is difficult due to factors like the similarity of pill forms and the scarcity of databases. The goal of this work is to improve deep learning models for better classification of pill images. A dataset of 994 images are utilized from a public pharmaceutical database which sorted by 20 common type of pills. These images were split into training, validation, and testing sets in a 70:15:15 ratio. There are three different models which are YOLOv3, YOLOv5, and YOLOv8 were employed to the system. These models use performance metrics like recall, mean Average Precision (mAP), and precision as results. According to our results, YOLOv8 did remarkably well, obtaining a precision and F1-score of 99.17% and 96.95%, respectively, while YOLOv5 great with mAP and recall of 94.83% and 95%, respectively, outperforming the YOLOv3 model. The success of YOLOv8 underscores its significance in reducing medical errors with its accurate, real-time capabilities for identifying pills. The use of artificial intelligence in pill recognition not only lowers the chance of incorrect medication use but also streamlines the duties of healthcare professionals. This shift allows them to prioritize crucial responsibilities and simplifies the process of pill identification. |
| first_indexed | 2025-11-15T03:49:53Z |
| format | Article |
| id | ump-43006 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T03:49:53Z |
| publishDate | 2024 |
| publisher | Penerbit UMP |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-430062024-12-03T04:05:33Z http://umpir.ump.edu.my/id/eprint/43006/ Pill Recognition via Deep Learning Approaches Mohd Rais Hakim, Ramlee Ismail, Mohd Khairuddin Zubaidah, Zamri Muhammad Nur Aiman, Shapiee Muhammad Amirul, Abdullah RS Pharmacy and materia medica TS Manufactures Deep learning significantly transforms pill imaging recognition in the healthcare and pharmaceutical industries by automating the identification and classification processes based on visual indicators. It is important to develop a robust deep learning framework to ensure the accurate dispensing of medications. The features such as size, color, shape, markings and text imprint are scrutinized by these methods. However, real-world matching is difficult due to factors like the similarity of pill forms and the scarcity of databases. The goal of this work is to improve deep learning models for better classification of pill images. A dataset of 994 images are utilized from a public pharmaceutical database which sorted by 20 common type of pills. These images were split into training, validation, and testing sets in a 70:15:15 ratio. There are three different models which are YOLOv3, YOLOv5, and YOLOv8 were employed to the system. These models use performance metrics like recall, mean Average Precision (mAP), and precision as results. According to our results, YOLOv8 did remarkably well, obtaining a precision and F1-score of 99.17% and 96.95%, respectively, while YOLOv5 great with mAP and recall of 94.83% and 95%, respectively, outperforming the YOLOv3 model. The success of YOLOv8 underscores its significance in reducing medical errors with its accurate, real-time capabilities for identifying pills. The use of artificial intelligence in pill recognition not only lowers the chance of incorrect medication use but also streamlines the duties of healthcare professionals. This shift allows them to prioritize crucial responsibilities and simplifies the process of pill identification. Penerbit UMP 2024-10-06 Article PeerReviewed pdf en cc_by_nc_4 http://umpir.ump.edu.my/id/eprint/43006/1/Pill%20Recognition%20via%20Deep%20Learning%20Approaches.pdf Mohd Rais Hakim, Ramlee and Ismail, Mohd Khairuddin and Zubaidah, Zamri and Muhammad Nur Aiman, Shapiee and Muhammad Amirul, Abdullah (2024) Pill Recognition via Deep Learning Approaches. Mekatronika - Journal of Intelligent Manufacturing & Mechatronics, 6 (2). pp. 88-95. ISSN 2637-0883. (Published) https://doi.org/10.15282/mekatronika.v6i2.11020 https://doi.org/10.15282/mekatronika.v6i2.11020 |
| spellingShingle | RS Pharmacy and materia medica TS Manufactures Mohd Rais Hakim, Ramlee Ismail, Mohd Khairuddin Zubaidah, Zamri Muhammad Nur Aiman, Shapiee Muhammad Amirul, Abdullah Pill Recognition via Deep Learning Approaches |
| title | Pill Recognition via Deep Learning Approaches |
| title_full | Pill Recognition via Deep Learning Approaches |
| title_fullStr | Pill Recognition via Deep Learning Approaches |
| title_full_unstemmed | Pill Recognition via Deep Learning Approaches |
| title_short | Pill Recognition via Deep Learning Approaches |
| title_sort | pill recognition via deep learning approaches |
| topic | RS Pharmacy and materia medica TS Manufactures |
| url | http://umpir.ump.edu.my/id/eprint/43006/ http://umpir.ump.edu.my/id/eprint/43006/ http://umpir.ump.edu.my/id/eprint/43006/ http://umpir.ump.edu.my/id/eprint/43006/1/Pill%20Recognition%20via%20Deep%20Learning%20Approaches.pdf |