Tea Disease Recognition Based on Image Segmentation and Data Augmentation
Accurate identification of tea leaf diseases is crucial for intelligent tea cultivation and monitoring. However, the complex environment of tea plantations—affected by weather variations and uneven lighting—poses significant challenges for building effective disease recognition...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10852315/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575589802835968 |
|---|---|
| author | Ji Li Chenyi Liao |
| author_facet | Ji Li Chenyi Liao |
| author_sort | Ji Li |
| collection | DOAJ |
| description | Accurate identification of tea leaf diseases is crucial for intelligent tea cultivation and monitoring. However, the complex environment of tea plantations—affected by weather variations and uneven lighting—poses significant challenges for building effective disease recognition models using raw field-captured images. To address this, we propose a method that combines two-stage image segmentation with an improved conditional generative adversarial network (IC-GAN). The two-stage segmentation approach, integrating graph cuts and support vector machines (SVM), effectively isolates disease regions from complex backgrounds. The IC-GAN augments the dataset by generating high-quality synthetic disease images for model training. Finally, an Inception Embedded Pooling Convolutional Neural Network (IDCNN) is developed for disease recognition. Experimental results demonstrate that the segmentation method improves recognition accuracy from 53.36% to 75.63%, while the IC-GAN increases the dataset size. The IDCNN achieves 97.66% accuracy, 97.36% recall, and a 96.98% F1 score across three types of tea diseases. Comparative evaluations on two additional datasets further confirm the method’s robustness and accuracy, offering a practical solution to reduce tea production losses and improve quality. |
| format | Article |
| id | doaj-art-6ec2d86524e3487a9b84fc30cd3cadec |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6ec2d86524e3487a9b84fc30cd3cadec2025-01-31T23:04:38ZengIEEEIEEE Access2169-35362025-01-0113196641967710.1109/ACCESS.2025.353402410852315Tea Disease Recognition Based on Image Segmentation and Data AugmentationJi Li0https://orcid.org/0009-0000-3816-165XChenyi Liao1https://orcid.org/0009-0007-7191-3607College of Bioscience and Biotechnology, Hunan Agricultural University, Changsha, ChinaSchool of Environmental and Chemical Engineering, Foshan University, Foshan, ChinaAccurate identification of tea leaf diseases is crucial for intelligent tea cultivation and monitoring. However, the complex environment of tea plantations—affected by weather variations and uneven lighting—poses significant challenges for building effective disease recognition models using raw field-captured images. To address this, we propose a method that combines two-stage image segmentation with an improved conditional generative adversarial network (IC-GAN). The two-stage segmentation approach, integrating graph cuts and support vector machines (SVM), effectively isolates disease regions from complex backgrounds. The IC-GAN augments the dataset by generating high-quality synthetic disease images for model training. Finally, an Inception Embedded Pooling Convolutional Neural Network (IDCNN) is developed for disease recognition. Experimental results demonstrate that the segmentation method improves recognition accuracy from 53.36% to 75.63%, while the IC-GAN increases the dataset size. The IDCNN achieves 97.66% accuracy, 97.36% recall, and a 96.98% F1 score across three types of tea diseases. Comparative evaluations on two additional datasets further confirm the method’s robustness and accuracy, offering a practical solution to reduce tea production losses and improve quality.https://ieeexplore.ieee.org/document/10852315/Conditional generative adversarial networkdisease recognitiondeep learningimage generation |
| spellingShingle | Ji Li Chenyi Liao Tea Disease Recognition Based on Image Segmentation and Data Augmentation IEEE Access Conditional generative adversarial network disease recognition deep learning image generation |
| title | Tea Disease Recognition Based on Image Segmentation and Data Augmentation |
| title_full | Tea Disease Recognition Based on Image Segmentation and Data Augmentation |
| title_fullStr | Tea Disease Recognition Based on Image Segmentation and Data Augmentation |
| title_full_unstemmed | Tea Disease Recognition Based on Image Segmentation and Data Augmentation |
| title_short | Tea Disease Recognition Based on Image Segmentation and Data Augmentation |
| title_sort | tea disease recognition based on image segmentation and data augmentation |
| topic | Conditional generative adversarial network disease recognition deep learning image generation |
| url | https://ieeexplore.ieee.org/document/10852315/ |
| work_keys_str_mv | AT jili teadiseaserecognitionbasedonimagesegmentationanddataaugmentation AT chenyiliao teadiseaserecognitionbasedonimagesegmentationanddataaugmentation |