Citation

Dipty, Ismotara and Assaduzzaman, Md and Fahad, Nafiz and Hossen, Md. Jakir and Haider, Md. Farhatul and Rahman, Fiaj (2025) TeaNet8: A real time Android application-based Tea Leaf Disease detection using fine-tuned transfer learning and Gradient-Weighted Class Activation Mapping visualization. Results in Control and Optimization, 20. p. 100577. ISSN 2666-7207

Text 21.pdf - Published Version Restricted to Repository staff only Download (4MB)

Abstract

Tea is widely regarded as one of the most popular beverages globally, and Bangladesh plays a significant role both as a producer and consumer of this renowned drink. However, diseases that impact the quality and productivity of crops can greatly impede the production of tea, impacting the final product’s quantity and quality. To prevent and control tea leaf diseases, a reliable and precise diagnosis and identification system is needed. Tea leaf infections are discovered manually, which takes time and affects crop quality and production. Detecting tea leaf disease early can lead to decreased damage to overall tea production. Advanced deep learning methods are simplifying the identification and categorization of specific illnesses in tea plants. This current study introduces TeaNet8, a deep learning-based approach for identifying and classifying eight tea leaf disease classes using a fine-tuned ResNet50V2 model. Moreover, this study employs 2824 images of eight different types of leaf diseases. Preprocessing techniques such as Contrast Limited Adaptive Histogram Equalization (CLAHE), brightness adjustment, and unsharp masking were applied to enhance the dataset. Additionally, data augmentation techniques were used to increase its diversity. The proposed model identify the differnt type of tea leaf disease with 97% accuracy.Gradient-Weighted Class Activation Mapping (Grad-CAM) visualization was employed to interpret and understand model predictions. The model demonstrated perfect accuracy for Algal Spot, Anthracnose, Gray Blight, and White Spot, with accuracy rates of 97.14% for Brown Blight, 94.59% for Healthy leaves, 94.12% for Red Spot, and 92.31% for Bird Eye Spot. Furthermore, the proposed model’s performance was compared against three pre-trained fine-tuning models. Various performance measurement indicators were used to evaluate the performance of the proposed model. The results showed that the proposed model is effective in categorizing diseases in tea leaves.Finally, An Android-based system was developed employing the most effective model to aid farmers for detecting tea leaf diseases.

Item Type:	Article
Uncontrolled Keywords:	Tea leaf, Transfer learning, Grad- CAM, Fine-tuning, Android application
Subjects:	L Education > LB Theory and practice of education > LB1060 Learning
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	27 Aug 2025 06:44
Last Modified:	27 Aug 2025 06:44
URII:	http://shdl.mmu.edu.my/id/eprint/14487

Downloads

Edit (login required)