A comprehensive hog plum leaf disease dataset for enhanced detection and classification.

Area of Science:

• Agricultural Science
• Computer Vision
• Plant Pathology

Background:

• Comprehensive datasets are crucial for developing AI-driven agricultural solutions.
• Hog plum (Spondias mombin) is a vital crop, but leaf diseases pose significant threats to productivity.
• Current disease management often relies on manual inspection, which can be time-consuming and error-prone.

Purpose of the Study:

• To create a comprehensive Hog plum leaf disease dataset for agricultural research.
• To facilitate the development of machine learning models for early disease detection and classification.
• To provide a benchmark dataset for training and testing automated monitoring systems.

Main Methods:

• Collected 3,782 images of Hog plum leaves from various regions in Bangladesh.
• Classified images into two categories: 'Healthy' and 'Insect hole'.
• Applied extensive data augmentation techniques (flipping, rotation, scaling, etc.) to expand the dataset to 20,000 images.

Main Results:

• Successfully created an augmented dataset of 20,000 Hog plum leaf images.
• The dataset includes healthy leaves and leaves with 'Insect hole' disease.
• The augmented dataset serves as a robust training set for deep learning models.

Conclusions:

• The developed Hog plum leaf disease dataset is essential for advancing precision agriculture.
• This dataset will enhance the accuracy and efficiency of automated disease detection systems.
• It supports sustainable agriculture by enabling timely interventions and reducing chemical usage.