Plant Leaf Recognition using OSSGabor filter and Vision Transformer
Deep learning methods are increasingly used in automated plant species classification systems to support biodiversity conservation and ecological monitoring, particularly for medicinal plants. This study presents a novel approach to plant leaf recognition by integrating the Vision Transformer (ViT)...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Graz University of Technology
2025-05-01
|
| Series: | Journal of Universal Computer Science |
| Subjects: | |
| Online Access: | https://lib.jucs.org/article/129624/download/pdf/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850184191489081344 |
|---|---|
| author | Thuy Phuong Khuat Trang Van Hoang Thien Van |
| author_facet | Thuy Phuong Khuat Trang Van Hoang Thien Van |
| author_sort | Thuy Phuong Khuat |
| collection | DOAJ |
| description | Deep learning methods are increasingly used in automated plant species classification systems to support biodiversity conservation and ecological monitoring, particularly for medicinal plants. This study presents a novel approach to plant leaf recognition by integrating the Vision Transformer (ViT) model with the OSSGabor filter, termed the OGViT method. The OSSGabor filter is a leaf feature extraction technique that combines the responses of Gabor filters in 16 directions and optimizes their parameters using the Structural Similarity Index Measure (SSIM). These features capture intricate details such as leaf veins, texture, and frequency variations, which are essential for enabling ViT to fully leverage deep learning for leaf recognition. Experimental results on four public datasets—Swedish Leaf, Flavia, Folio, and UCI Leaf—demonstrate that the OGViT method outperforms state-of-the-art approaches, achieving accuracy scores of 100%, 100%, 100%, and 98.88%, respectively, with a 20% testing set and an 80% training set. This performance highlights the effectiveness of the proposed method for plant classification, offering a robust tool with potential applications in agriculture and biodiversity conservation.  |
| format | Article |
| id | doaj-art-3be36040b68840b9a87d90b8e34a5e4e |
| institution | OA Journals |
| issn | 0948-6968 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Graz University of Technology |
| record_format | Article |
| series | Journal of Universal Computer Science |
| spelling | doaj-art-3be36040b68840b9a87d90b8e34a5e4e2025-08-20T02:17:06ZengGraz University of TechnologyJournal of Universal Computer Science0948-69682025-05-0131662364710.3897/jucs.129624129624Plant Leaf Recognition using OSSGabor filter and Vision TransformerThuy Phuong Khuat0Trang Van1Hoang Thien Van2HUTECH UniversityHo Chi Minh City University of Economics and FinanceHUTECH UniversityDeep learning methods are increasingly used in automated plant species classification systems to support biodiversity conservation and ecological monitoring, particularly for medicinal plants. This study presents a novel approach to plant leaf recognition by integrating the Vision Transformer (ViT) model with the OSSGabor filter, termed the OGViT method. The OSSGabor filter is a leaf feature extraction technique that combines the responses of Gabor filters in 16 directions and optimizes their parameters using the Structural Similarity Index Measure (SSIM). These features capture intricate details such as leaf veins, texture, and frequency variations, which are essential for enabling ViT to fully leverage deep learning for leaf recognition. Experimental results on four public datasets—Swedish Leaf, Flavia, Folio, and UCI Leaf—demonstrate that the OGViT method outperforms state-of-the-art approaches, achieving accuracy scores of 100%, 100%, 100%, and 98.88%, respectively, with a 20% testing set and an 80% training set. This performance highlights the effectiveness of the proposed method for plant classification, offering a robust tool with potential applications in agriculture and biodiversity conservation. https://lib.jucs.org/article/129624/download/pdf/Plant classificationSSIMGabor FilterVision T |
| spellingShingle | Thuy Phuong Khuat Trang Van Hoang Thien Van Plant Leaf Recognition using OSSGabor filter and Vision Transformer Journal of Universal Computer Science Plant classification SSIM Gabor Filter Vision T |
| title | Plant Leaf Recognition using OSSGabor filter and Vision Transformer |
| title_full | Plant Leaf Recognition using OSSGabor filter and Vision Transformer |
| title_fullStr | Plant Leaf Recognition using OSSGabor filter and Vision Transformer |
| title_full_unstemmed | Plant Leaf Recognition using OSSGabor filter and Vision Transformer |
| title_short | Plant Leaf Recognition using OSSGabor filter and Vision Transformer |
| title_sort | plant leaf recognition using ossgabor filter and vision transformer |
| topic | Plant classification SSIM Gabor Filter Vision T |
| url | https://lib.jucs.org/article/129624/download/pdf/ |
| work_keys_str_mv | AT thuyphuongkhuat plantleafrecognitionusingossgaborfilterandvisiontransformer AT trangvan plantleafrecognitionusingossgaborfilterandvisiontransformer AT hoangthienvan plantleafrecognitionusingossgaborfilterandvisiontransformer |