BDMANGO: A dataset for identifying Bangladeshi mango types through mango leaves

The field of agriculture, particularly in the context of machine learning applications, requires quality datasets for advancing research and development. Recognizing the diverse and unique characteristics of mango varieties in Bangladesh, we have created a comprehensive and publicly accessible dataset titled "Mango Leaf Classification". This dataset aims to address the challenges of identifying different mango leaf types by providing images essential for research. Collected from two distinct locations, the dataset includes images of six mango varieties: Amrapali, Banana, Chaunsa, Fazli, Haribhanga, and Himsagar. Images were captured using the rear cameras of a Google Pixel 6a and an iPhone XR, and then resized to 640 × 480 pixels. Both sides of each mango leaf were photographed, using white paper as the background, to accurately reflect real-world scenarios in mango cultivation fields. Additionally, using image augmentation techniques such as rotation, horizontal flip, vertical flip, width shift, height shift, shear range, and zooming, the dataset has been expanded from 837 original images to a total of 5,859 images. These augmented images significantly enhance the dataset's utility for training, testing, and validating machine learning models designed for classifying mango leaf varieties, thereby supporting research efforts in this domain.