Rose Leaf Nutritient Deficiency Dataset

Title: Rose Leaf Nutritional Deficiency Dataset

Authors: Abu Raihan, Abdul Hasib Uddin, Syed Muntasin Fayaz, Jafrul Sadik, Meraj Ahmmed

Affiliations: Department of Computer Science and Engineering, Khwaja Yunus Ali University, Sirajganj, Bangladesh

Description:
This dataset contains high-resolution images of rose leaves affected by four nutrient deficiencies—heat stress, magnesium deficiency, phosphorus deficiency, and iron deficiency—along with a healthy leaf class. The images were collected over six months from multiple rose gardens in Sirajganj, Bangladesh, using various smartphone cameras under natural lighting. After pre-processing, 539 raw images were retained, and augmentation increased the dataset to 1,500 images. The dataset is well-structured and serves as a benchmark for training machine learning and deep learning models for automated plant health assessment.

Subject Areas: Computer Science, Agriculture Science, AI, Computer Vision, Pattern Recognition

Data Format: JPG images (processed and filtered)

Data Collection:

Captured with smartphones (Redmi Note 10 Pro Max, iPhone 8, Realme X) in different lighting conditions.
Organized into five labeled categories, split into an 80:20 ratio for training and testing.
Usage Notes:
Ideal for developing AI models in plant health classification, image-based diagnosis, and precision agriculture. It supports early nutrient deficiency detection, improving rose cultivation efficiency.