Hyperspectral Images of Grapevine Leaves for Disease Detection

Elias Alisaac's dataset contains hyperspectral images of detached grapevine leaves used to detect and discriminate yellows diseases and other stresses. The images were acquired in the spectral range of 400-1,000 nm from leaves affected by diseases like Flavescence dorée, Bois noir, and nutrient deficiencies. The dataset was last updated on March 19, 2026.

Use Cases

• Training classification models to distinguish grapevine yellows diseases based on hyperspectral leaf signatures.
• Developing mobile monitoring platforms for large-scale disease diagnosis based on the described imaging method.
• Analyzing spectral differences between biotic stresses (virus, leafhopper) and abiotic stresses (iron, magnesium deficiency).

Strengths

• Hyperspectral images cover a specific spectral range of 400-1,000 nm.
• Classification models trained on the data achieved F1-scores exceeding 95% for black cultivars across six classes.
• The dataset is licensed under CC-BY-4.0 for open use.

Limitations

• Row count and column-level documentation are absent; data structure must be inferred after download.
• The dataset is 1.0 MB, which suggests a small scale of images or samples.
• The primary data file is a DOCX document, which may not contain raw image data directly.

Provenance

Source

figshare

Collection Method

Hyperspectral images were acquired using a mobile platform in the laboratory or in the field.

Freshness

Last updated 2026-03-19 06:48:17.