Multi-Class Fruit Leaf Classification Dataset (10 Classes)

This dataset comprises 3,173 high-quality images of healthy fruit leaves from 10 different classes, specifically curated for research in plant classification, species identification, and agricultural analysis using deep learning and computer vision techniques. The dataset includes images of Aegle marmelos (336), Black plum (304), Custard Apple (304), Guava (325), Jackfruit (311), Lotkon (306), Lychee (312), Mango (330), Plum (302), and Star Fruit (343). Each image was captured under diverse environmental conditions to ensure a robust dataset for training and evaluating machine learning models. Since all images represent healthy leaves, this dataset can serve as a baseline for plant disease detection, enabling researchers to compare healthy and diseased samples effectively. It is well-suited for image classification, feature extraction, transfer learning, and species recognition in the fields of agriculture and botany. Potential applications include training convolutional neural networks (CNNs) and transformer-based models for fruit leaf classification, fine-tuning pre-trained models, and developing AI-driven plant monitoring and smart agriculture solutions. The dataset also serves as a valuable resource for augmenting existing datasets to improve model generalization. Researchers and AI practitioners can leverage this dataset to advance precision agriculture and plant health monitoring. For any inquiries or collaboration, please contact the authors.