Segmentation Studies on Al‐Si‐Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss Functions
ABSTRACT Segmenting metallographic pictures is being done in material science and related domains in order to detect the features within them. Therefore, it becomes crucial to find grains and secondary phase particles. It is necessary to label every pixel in order to obtain satisfactory segmentation...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-04-01
|
| Series: | Engineering Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/eng2.70119 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849324301073776640 |
|---|---|
| author | Abeyram M. Nithin Murukessan Perumal M. J. Davidson M. Srinivas C. S. P. Rao Katika Harikrishna Jayant Jagtap Abhijit Bhowmik A. Johnson Santhosh |
| author_facet | Abeyram M. Nithin Murukessan Perumal M. J. Davidson M. Srinivas C. S. P. Rao Katika Harikrishna Jayant Jagtap Abhijit Bhowmik A. Johnson Santhosh |
| author_sort | Abeyram M. Nithin |
| collection | DOAJ |
| description | ABSTRACT Segmenting metallographic pictures is being done in material science and related domains in order to detect the features within them. Therefore, it becomes crucial to find grains and secondary phase particles. It is necessary to label every pixel in order to obtain satisfactory segmentation outcomes. However, labeling takes a lot of time and is physically taxing. Therefore, in order to obtain higher performance, we have suggested a semi‐supervised deep learning technique in the current study that uses fewer labeled images. Other deep learning algorithms, such as Segnet, Resnet, and FCN, were compared with the Unet approach that was suggested. Additional comparisons have been made using the Dice score (0.85), IOU score (0.74), F1 (0.85), and recall (0.96) measures. Different loss functions were also compared, including binary, SS loss, and Tversky. Furthermore, the dataset was expanded, and these datasets were also subjected to result analysis. The trials show that, both numerically and qualitatively, the suggested approach can produce superior outcomes with fewer labeled photos. |
| format | Article |
| id | doaj-art-3cd13dfd1b09472b8589e3093bdcd7db |
| institution | Kabale University |
| issn | 2577-8196 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | Engineering Reports |
| spelling | doaj-art-3cd13dfd1b09472b8589e3093bdcd7db2025-08-20T03:48:46ZengWileyEngineering Reports2577-81962025-04-0174n/an/a10.1002/eng2.70119Segmentation Studies on Al‐Si‐Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss FunctionsAbeyram M. Nithin0Murukessan Perumal1M. J. Davidson2M. Srinivas3C. S. P. Rao4Katika Harikrishna5Jayant Jagtap6Abhijit Bhowmik7A. Johnson Santhosh8Department of Mechanical Engineering Sreenidhi Institute of Science and Technology Hyderabad IndiaDepartment of Computer Science Engineering NIT Warangal Warangal IndiaDepartment of Mechanical Engineering NIT Warangal Warangal IndiaDepartment of Computer Science Engineering NIT Warangal Warangal IndiaDepartment of Mechanical Engineering NIT Andhra Pradesh Andhra Pradesh IndiaDepartment of Mechanical Engineering Shri Vishnu Engineering College for Women Bhimavaram IndiaDepartment of Computing Science and Artificial Intelligence, NIMS Institute of Engineering & Technology NIMS University Rajasthan Jaipur IndiaDepartment of Mechanical Engineering Dream Institute of Technology Kolkata IndiaFaculty of Mechanical Engineering Jimma Institute of Technology Jimma EthiopiaABSTRACT Segmenting metallographic pictures is being done in material science and related domains in order to detect the features within them. Therefore, it becomes crucial to find grains and secondary phase particles. It is necessary to label every pixel in order to obtain satisfactory segmentation outcomes. However, labeling takes a lot of time and is physically taxing. Therefore, in order to obtain higher performance, we have suggested a semi‐supervised deep learning technique in the current study that uses fewer labeled images. Other deep learning algorithms, such as Segnet, Resnet, and FCN, were compared with the Unet approach that was suggested. Additional comparisons have been made using the Dice score (0.85), IOU score (0.74), F1 (0.85), and recall (0.96) measures. Different loss functions were also compared, including binary, SS loss, and Tversky. Furthermore, the dataset was expanded, and these datasets were also subjected to result analysis. The trials show that, both numerically and qualitatively, the suggested approach can produce superior outcomes with fewer labeled photos.https://doi.org/10.1002/eng2.70119augmentationCNNlabelingloss functionUnet |
| spellingShingle | Abeyram M. Nithin Murukessan Perumal M. J. Davidson M. Srinivas C. S. P. Rao Katika Harikrishna Jayant Jagtap Abhijit Bhowmik A. Johnson Santhosh Segmentation Studies on Al‐Si‐Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss Functions Engineering Reports augmentation CNN labeling loss function Unet |
| title | Segmentation Studies on Al‐Si‐Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss Functions |
| title_full | Segmentation Studies on Al‐Si‐Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss Functions |
| title_fullStr | Segmentation Studies on Al‐Si‐Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss Functions |
| title_full_unstemmed | Segmentation Studies on Al‐Si‐Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss Functions |
| title_short | Segmentation Studies on Al‐Si‐Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss Functions |
| title_sort | segmentation studies on al si mg metallographic images using various different deep learning algorithms and loss functions |
| topic | augmentation CNN labeling loss function Unet |
| url | https://doi.org/10.1002/eng2.70119 |
| work_keys_str_mv | AT abeyrammnithin segmentationstudiesonalsimgmetallographicimagesusingvariousdifferentdeeplearningalgorithmsandlossfunctions AT murukessanperumal segmentationstudiesonalsimgmetallographicimagesusingvariousdifferentdeeplearningalgorithmsandlossfunctions AT mjdavidson segmentationstudiesonalsimgmetallographicimagesusingvariousdifferentdeeplearningalgorithmsandlossfunctions AT msrinivas segmentationstudiesonalsimgmetallographicimagesusingvariousdifferentdeeplearningalgorithmsandlossfunctions AT csprao segmentationstudiesonalsimgmetallographicimagesusingvariousdifferentdeeplearningalgorithmsandlossfunctions AT katikaharikrishna segmentationstudiesonalsimgmetallographicimagesusingvariousdifferentdeeplearningalgorithmsandlossfunctions AT jayantjagtap segmentationstudiesonalsimgmetallographicimagesusingvariousdifferentdeeplearningalgorithmsandlossfunctions AT abhijitbhowmik segmentationstudiesonalsimgmetallographicimagesusingvariousdifferentdeeplearningalgorithmsandlossfunctions AT ajohnsonsanthosh segmentationstudiesonalsimgmetallographicimagesusingvariousdifferentdeeplearningalgorithmsandlossfunctions |