Back to datasets
Dataset assetOpen Source CommunityComputer VisionPlant Disease Detection

PlantDoc

PlantDoc is a dataset for visual plant disease detection, containing 2,598 data points covering 13 plant species and up to 17 disease classes, annotated manually over approximately 300 hours from images scraped from the Internet. The dataset aims to achieve early detection of plant diseases via computer‑vision methods, improving classification accuracy by up to 31%.

Source
github
Created
Sep 10, 2019
Updated
May 22, 2024
Signals
809 views
Availability
Linked source ready
Overview

Dataset description and usage context

PlantDoc Dataset Overview

Dataset Name

PlantDoc: A Dataset for Visual Plant Disease Detection

Dataset Purpose

Benchmark for classification models for visual plant disease detection.

Dataset Content

  • Contains 2,598 data points.
  • Covers 13 plant species.
  • Involves up to 17 disease categories.
  • Images were scraped from the Internet and manually annotated over ~300 hours.

Dataset Contribution

  • Models trained on this dataset can improve plant disease classification accuracy by up to 31%.
  • Aims to lower the barrier for applying computer‑vision techniques to plant disease detection.

Related Literature

  • Full paper available at Arxiv and ACM.

Dataset Authors

Davinder Singh, Naman Jain, Pranjali Jain, Pratik Kayal, Sudhakar Kumawat, Nipun Batra

Dataset License

Creative Commons Attribution 4.0 International

Need downstream help?

Pair the dataset with AI analysis and content workflows.

Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.

Explore AI studio