A deep learning method for differentiating safflower germplasm using optimal leaf structure features
Medicinal plants, such as safflower (Carthamustinctorius), are essential in both conventional and modern healthcare. This study evaluatesthe reliability of leaf image classification for differentiating safflower germplasm accessions, despite the challenge posed by similar leaf structures across vari...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S157495412500007X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595404907085824 |
|---|---|
| author | Hoang Thien Van Phuong Thuy Khuat Trang Van Thai Thanh Tuan Yong Suk Chung |
| author_facet | Hoang Thien Van Phuong Thuy Khuat Trang Van Thai Thanh Tuan Yong Suk Chung |
| author_sort | Hoang Thien Van |
| collection | DOAJ |
| description | Medicinal plants, such as safflower (Carthamustinctorius), are essential in both conventional and modern healthcare. This study evaluatesthe reliability of leaf image classification for differentiating safflower germplasm accessions, despite the challenge posed by similar leaf structures across varieties. Traditional classification methods can be time-consuming and error prone, underscoring the need for fine-grained classification techniques. To address this, we introduce a novel comprehensive leaf database of safflower varieties that is meticulously curated by experts. This database can be used to support future research. We evaluate state-of-the-art deep learning methods for classifying safflower varieties and propose a novel approach using a Vision Transformer (ViT) model with an optimal leaf structure feature (OLSF). The OLSF, calculated as the average response of a multidirectional Gabor filter bank and optimized with the structural similarity index measure (SSIM), enhances complex leaf features, such as veins, texture, and frequency variations, to enhance the classification performance of deep learning models. The experimental results reveal that the OLSF-ViT model achieves excellent accuracy scores of 100 %, 99.05 %, and 89.65 % on the Folio, UCI Leaves, and JNUSafflower datasets, respectively. These findings demonstrate that leaf image analysis is an effective and affordable tool for investigating the phenotypic diversity among safflower cultivars. This study highlights the potential of OLSF-ViT in automatic plant classification, and the results can be used in plant science, herbal medicine, and biodiversity conservation. |
| format | Article |
| id | doaj-art-7ceb950de19a4898b4a7504d33a8c00a |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-7ceb950de19a4898b4a7504d33a8c00a2025-01-19T06:24:45ZengElsevierEcological Informatics1574-95412025-03-0185102998A deep learning method for differentiating safflower germplasm using optimal leaf structure featuresHoang Thien Van0Phuong Thuy Khuat1Trang Van2Thai Thanh Tuan3Yong Suk Chung4Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Viet Nam; Corresponding authors.Computer Science Center, University of Science, VNU-HCM, HUTECH University, Ho Chi Minh City, Viet NamFaculty of Information Technology, Ho Chi Minh City University of Economics and Finance, Ho Chi Minh City, Viet NamUniversity of Information Technology, VNU-HCM, Ho Chi Minh city, Viet NamDepartment of Plant Resources and Environment, Jeju National University, Jeju, Republic of Korea; Corresponding authors.Medicinal plants, such as safflower (Carthamustinctorius), are essential in both conventional and modern healthcare. This study evaluatesthe reliability of leaf image classification for differentiating safflower germplasm accessions, despite the challenge posed by similar leaf structures across varieties. Traditional classification methods can be time-consuming and error prone, underscoring the need for fine-grained classification techniques. To address this, we introduce a novel comprehensive leaf database of safflower varieties that is meticulously curated by experts. This database can be used to support future research. We evaluate state-of-the-art deep learning methods for classifying safflower varieties and propose a novel approach using a Vision Transformer (ViT) model with an optimal leaf structure feature (OLSF). The OLSF, calculated as the average response of a multidirectional Gabor filter bank and optimized with the structural similarity index measure (SSIM), enhances complex leaf features, such as veins, texture, and frequency variations, to enhance the classification performance of deep learning models. The experimental results reveal that the OLSF-ViT model achieves excellent accuracy scores of 100 %, 99.05 %, and 89.65 % on the Folio, UCI Leaves, and JNUSafflower datasets, respectively. These findings demonstrate that leaf image analysis is an effective and affordable tool for investigating the phenotypic diversity among safflower cultivars. This study highlights the potential of OLSF-ViT in automatic plant classification, and the results can be used in plant science, herbal medicine, and biodiversity conservation.http://www.sciencedirect.com/science/article/pii/S157495412500007XSafflowerPlant classificationGabor filterVision transformerDeep learning |
| spellingShingle | Hoang Thien Van Phuong Thuy Khuat Trang Van Thai Thanh Tuan Yong Suk Chung A deep learning method for differentiating safflower germplasm using optimal leaf structure features Ecological Informatics Safflower Plant classification Gabor filter Vision transformer Deep learning |
| title | A deep learning method for differentiating safflower germplasm using optimal leaf structure features |
| title_full | A deep learning method for differentiating safflower germplasm using optimal leaf structure features |
| title_fullStr | A deep learning method for differentiating safflower germplasm using optimal leaf structure features |
| title_full_unstemmed | A deep learning method for differentiating safflower germplasm using optimal leaf structure features |
| title_short | A deep learning method for differentiating safflower germplasm using optimal leaf structure features |
| title_sort | deep learning method for differentiating safflower germplasm using optimal leaf structure features |
| topic | Safflower Plant classification Gabor filter Vision transformer Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S157495412500007X |
| work_keys_str_mv | AT hoangthienvan adeeplearningmethodfordifferentiatingsafflowergermplasmusingoptimalleafstructurefeatures AT phuongthuykhuat adeeplearningmethodfordifferentiatingsafflowergermplasmusingoptimalleafstructurefeatures AT trangvan adeeplearningmethodfordifferentiatingsafflowergermplasmusingoptimalleafstructurefeatures AT thaithanhtuan adeeplearningmethodfordifferentiatingsafflowergermplasmusingoptimalleafstructurefeatures AT yongsukchung adeeplearningmethodfordifferentiatingsafflowergermplasmusingoptimalleafstructurefeatures AT hoangthienvan deeplearningmethodfordifferentiatingsafflowergermplasmusingoptimalleafstructurefeatures AT phuongthuykhuat deeplearningmethodfordifferentiatingsafflowergermplasmusingoptimalleafstructurefeatures AT trangvan deeplearningmethodfordifferentiatingsafflowergermplasmusingoptimalleafstructurefeatures AT thaithanhtuan deeplearningmethodfordifferentiatingsafflowergermplasmusingoptimalleafstructurefeatures AT yongsukchung deeplearningmethodfordifferentiatingsafflowergermplasmusingoptimalleafstructurefeatures |