ABCGMP Fruit and Leaf Disease Six Crop Dataset

Contributors: Dr. Neeta Nain
Research Scholars: Anand Kumar Jain
Institute: Malaviya National Institute of Technology Jaipur
Anadi Jain
Institute: Government women engineering College Ajmer ( Bikaner Technical University, Bikaner)
Domain Expert: Kota Agriculture University, Kota and Rajsthan Government Agriculture Department
Crops: Apple, Banana, Citrus, Guava, Mango, Papaya
Apple: Healthy Fruit, Disease Fruit, Healthy Leaf, Black Rot
Banana: Healthy Fruit, Disease Fruit, Healthy Leaf, cordana
Citrus: Healthy Fruit, Disease Fruit, Healthy Leaf, Cancker Leaf
Guava: Healthy Fruit, Disease Fruit, Healthy Leaf, Red Rust
Mango: Healthy Fruit, Disease Fruit, Healthy Leaf, Bacterial Canker
Papaya Disease: Ring Spot, Healthy leaf. Healthy Fruit, Disease Fruit.
Expert Ground-truth annotations, includ.ing soil health, humidity, nutrient deficiency, and pathological reports. Validated:

Plant diseases affecting both fruit and leaf tissues pose a major threat to crop yield, quality, and sustainable agricultural production. To support the development of robust artificial intelligence (AI) and deep learning–based disease diagnosis systems, a six-crop fruit and leaf disease image dataset has been curated, encompassing Apple, Banana, Citrus, Guava, Mango, and Papaya crops. This dataset captures a wide range of disease symptoms, infection stages, and visual variations observed under real cultivation conditions, including differences in color, texture, shape, and lesion patterns on both leaves and fruits.
The inclusion of multiple fruit crops enhances cross-crop generalization, enabling models to learn both crop-specific and shared pathological characteristics. High intra-class and inter-class diversity in lighting, background, and disease severity makes the dataset well-suited for training and evaluating lightweight convolutional neural networks, attention-based models, and multi-crop disease classification frameworks. Overall, this six-crop dataset serves as a valuable benchmark for advancing automated, scalable, and accurate plant disease detection systems for precision agriculture and smart farming applications.