Comprehensive Betel Leaf Disease Dataset for Advanced Pathology Research

Betel leaf is widely consumed in South Asian countries, and it has significant economic importance for its nutrient components. It has several types of uses, which highly increase its importance in the agricultural sector of South Asian countries. The cultivation of betel leaf is not easy, and it is highly prone to several types of diseases. Diseases decrease the quality of this leaf, which is a great threat to its cultivation. To get a good price from selling betel leaf, farmers are needed to ensure its leaf quality. For this reason, disease diagnosis is highly crucial for betel leaf farming. Moreover, betel leaf is a highly crucial export product, and it has a growing demand in the international market. Automated disease diagnosis can play a vital role in this process, which will also increase the actability of betel leaf in the international market.

To address the above-mentioned issue, advanced research on betel leaf disease diagnosis is needed. To support this, this dataset is developed by collecting images from betel cultivation fields using a smartphone. A total of 2,037 images are collected from four different cultivation fields in Bangladesh. Among 2,037 images, 1,080 images are healthy leaf images and 957 images are disease-affected leaf images. This dataset contains images of two betel leaf diseases, which are leaf rot and leaf spot, 269 and 688 images, respectively. The size of all images is 1024x1024 pixels, which will support almost all computer vision methods.

Several image augmentation techniques are utilized to make this dataset more comprehensive and support advanced pathology research. Different image augmentation techniques such as vertical and horizontal flips, brightness, and rotation are used in this dataset to generate 10,185 images from original images. These images will play a vital role in preventing overfitting and underfitting issues. This dataset contains a total of 12,222 images of three different classes such as healthy, leaf rot, and leaf spot.

Using this dataset, researchers can perform both classical and modern computer vision-based techniques to diagnose and analyze betel leaf diseases. This dataset can play a significant role in advanced pathology research for efficient and accurate disease diagnosis of betel leaf, which is highly crucial for sustainable development in betel leaf farming.