Publisher

STTSSTTS

Journal INSYST: Journal of Intelligent System and ComputationINSYST: Journal of Intelligent System and Computation Abstract

Mango plants (Mangifera indica) are a significant export commodity in the horticultural industry, offering numerous nutritional and economic benefits. They are rich in essential micronutrients, vitamins, and phytochemicals, contributing to their high demand globally. However, mango plants are susceptible to various diseases that can severely impact their yield and quality. These diseases pose a challenge to mango farmers, many of whom struggle to identify and treat them effectively, leading to potential harvest failures. This study aims to address this challenge by implementing a Deep Learning approach to classify diseases in mango leaves. Specifically, the research utilizes a Convolutional Neural Network (CNN) with DenseNet architecture, known for its efficiency in image classification tasks. The study incorporates Contrast Limited Adaptive Histogram Equalization (CLAHE) for image preprocessing to enhance detail and improve the models performance. Transfer Learning is utilized to optimize the DenseNet model, leveraging a pre-trained model to achieve high accuracy even with a relatively small dataset.

Conclusion

The DenseNet model presented in this study achieved remarkable accuracy in classifying mango leaf diseases, demonstrating its effectiveness in distinguishing between different disease categories and healthy leaves.The use of CLAHE significantly improved the detail in the images, making it easier for the model to identify disease features.Data augmentation techniques, including random rotation and flipping, increased the diversity of the dataset, contributing to the models robustness and accuracy.Transfer Learning played a vital role in optimizing the DenseNet models performance, allowing the study to achieve high accuracy with a relatively small dataset.The findings of this study have significant practical implications for the agricultural industry, particularly for mango farmers, as the high accuracy of the DenseNet model provides a valuable tool for identifying and managing mango leaf diseases more effectively.

Future Research

To further enhance the models performance and robustness, future research could explore the implementation of ensemble learning techniques. By combining multiple models, such as DenseNet with other advanced architectures, the models classification accuracy can be boosted. Additionally, expanding the dataset to include a larger number of images and diverse disease categories would improve the models generalizability and ability to handle a broader range of classifications. Furthermore, investigating the impact of different data augmentation techniques and their optimal combinations could lead to further improvements in the models accuracy and reliability.

References

1. Detection of mango leaf disease using the convolution neural network method | TEKNOSAINS : Jurnal Sains,... jurnal.sttmcileungsi.ac.id/index.php/tekno/article/view/639Detection of mango leaf disease using the convolution neural network method TEKNOSAINS Jurnal Sains jurnal sttmcileungsi ac index php tekno article view 639
2. Implementation of DenseNet Architecture With Transfer Learning to Classify Mango Leaf Diseases | INSYST:... doi.org/10.52985/insyst.v6i2.401Implementation of DenseNet Architecture With Transfer Learning to Classify Mango Leaf Diseases INSYST doi 10 52985 insyst v6i2 401
3. The Development of Image Classification Models Based on Computer Vision | Highlights in Science, Engineering... drpress.org/ojs/index.php/HSET/article/view/5505The Development of Image Classification Models Based on Computer Vision Highlights in Science Engineering drpress ojs index php HSET article view 5505

Metadata

File size	791.02 KB
Pages	9
DMCA	Report