Banana Leaf Spot Diseases (BananaLSD) Dataset for Classification of Banana Leaf Diseases Using Machine Learning

* Banana leaves are susceptible to several diseases, which have a significant impact on their yield. These diseases can cause damage to banana plants, resulting in reduced fruit production, stunted growth, and even plant death. As a result, affected plants are often unable to produce marketable fruit, leading to economic losses for banana farmers and potentially affecting the overall global banana supply.
* The dataset contains images of 3 prominent banana leaf spot diseases: (a) Sigatoka (b) Cordana and (c) Pestalotiopsis. It also contains images of healthy leaves.
* The dataset is split into 2 sets: (a) Original Set and (b) Augmented Set.
* The raw set contains 937 RGB images of four classes in JPG format.
* The augmented set contains 400 images for each class, totalling 1600 images. The following augmentation operations are performed: gaussian blur, horizontal flip, crop, linear contrast, shear, translate, and rotate shear.
All images have a standard resolution of 224 x 224 pixels.
* All images are captured using smartphone camera from banana fields of Bangabandhu Sheikh Mujibur Rahman Agricultural University, Bangladesh and adjacent banana fields during June 2021. Three smartphone cameras were used to collect the data. All images are labelled accordingly by a plant pathologist.