---
title: PlantVillage Apple Leaf Disease Dataset
url: https://www.emergentmind.com/topics/plantvillage-apple-leaf-disease-dataset
type: topic
---

# PlantVillage Apple Leaf Disease Dataset

The PlantVillage Apple Leaf Disease Dataset is a curated collection of labeled digital images of apple leaves exhibiting various disease symptoms and healthy conditions, designed as a benchmark for machine learning-based plant pathology. Originating from the PlantVillage initiative, with subsequent extensions and rigorous academic analyses, this dataset has become the reference standard for evaluating disease recognition algorithms in data-driven precision agriculture.

## 1. Dataset Composition and Class Taxonomy

The canonical PlantVillage Apple Leaf Disease dataset consists of expert-verified RGB images of isolated apple leaves, annotated for visually detectable disease symptoms. The four principal categories are:

- Apple scab (Venturia inaequalis)
- Apple black rot (Botryosphaeria obtusa)
- Cedar apple rust (Gymnosporangium juniperi-virginianae)
- Healthy (no visible symptoms)

Reported class distributions vary slightly across publications due to subset selection:

| Source                                   | Apple Scab | Black Rot | Cedar Rust | Healthy | Total |
|-------------------------------------------|------------|-----------|------------|---------|-------|
| [1511.08060] (original PV release)        | 630        | 621       | 276        | 1,645   | 3,172 |
| [2601.21307] (Mam-App)                    | 630        | 621       | 275        | 1,645   | 3,171 |
| [2504.20419] (GPT-4o/ResNet-50 subset)    | 631        | 622       | 276        | 1,646   | 3,175 |
| [2304.06520] (EfficientNetV2S)            | ~630       | ~620      | 275        | 1,645   | 3,171 |

The "PV-ALE" extension adds Alternaria leaf spot (85 images) and powdery mildew (127 images) with more complex backgrounds, raising the total to 3,383 images and broadening the taxonomy to six classes [2410.22490].

## 2. Image Acquisition Protocols and Preprocessing

Most images were acquired using controlled laboratory setups—detached leaves photographed under varied natural light against uniform gray or black paper, at high native resolution (e.g., Sony DSC-RX100, ~20 MP). For the original PlantVillage images, 4–7 orientations per leaf were captured to document morphological variability [1511.08060]. Later studies typically downsampled all images to 225–256 px squares to accommodate deep learning backbones [1604.03169, 2601.21307, 2304.06520, 2410.22490].

Key preprocessing procedures include:
- Manual cropping to minimize background content and standardize orientation (tip up)
- Pixel-value normalization ([0,1] or channel-wise zero-mean/unit-variance)
- Consistent train/validation/test splits, commonly stratified at 60/20/20 or 70/15/15 ratios, with patient-level grouping to avoid data leakage [2601.21307, 2304.06520]

Data augmentation is selectively applied during training. Techniques span random flips, rotations (±10° to ±30°), brightness adjustment, and geometric shear/shifts—parameters are explicitly tabulated in works such as [2601.21307] and [2304.06520].

## 3. Annotation and Curation Procedures

All PlantVillage apple images are annotated by plant pathology experts, either via field diagnosis during deliberate inoculation trials or from sentinel plots. Only specimens with diagnostic consensus are admitted [1511.08060]. For PV-ALE, newly sourced disease classes undergo strict human verification, URL/source filtering, and, where possible, further cropping or background minimization [2410.22490].

Leaf-level labeling is enforced to prevent multiple views of the same specimen from propagating between training and evaluation splits, mitigating information leakage [1604.03169].

## 4. Benchmarking, Evaluation Protocols, and Model Performance

Standard performance metrics include accuracy, precision, recall, and $F_1$-score, all per the following formulae (using the notation in [2304.06520, 2410.22490]):

\[
\mathrm{Accuracy} = \frac{TP + TN}{TP + FP + TN + FN}
\]
\[
\mathrm{Precision} = \frac{TP}{TP + FP}, \quad
\mathrm{Recall} = \frac{TP}{TP + FN}, \quad
F_1 = 2 \frac{\mathrm{Precision} \cdot \mathrm{Recall}}{\mathrm{Precision} + \mathrm{Recall}}
\]

Recent studies have achieved the following peak test-set performance on the canonical 4-class dataset:
- **Mam-App (Mamba, 0.051M params):** 99.58% accuracy, 99.30% precision, 99.14% recall, 99.22% $F_1$-score [2601.21307]
- **EfficientNetV2S (transfer learning, augmented):** 99.21% accuracy, 99.15% precision, 99.10% recall, 99.12% $F_1$-score [2304.06520]
- **ResNet-50 (fine-tuned):** 96.88% at 256px input, 0.969 $F_1$ [2504.20419]
- **ResNet-34 (Fastai):** 93.8% accuracy [2107.12598]

Extensions—including PV-ALE—demonstrate a reduction in $F_1$ from 99.63% (original) to 97.87% (extended, 6 classes, ResNet-50) due to class imbalance, low-resolution additions, and complex backgrounds [2410.22490].

## 5. Dataset Biases, Artifacts, and Limitations

Capture bias—inadvertent correlation between label and image background or acquisition parameters—is explicitly exposed in [2206.04374], where a random forest trained on the RGB values of just 8 background pixels achieves 49.0% accuracy (random chance for 38 classes is 2.6%). This demonstrates that consistent background, lighting, and equipment contribute dataset-specific signal exploitable by classifiers, even in the absence of leaf content.

Attempts to mitigate such bias via background removal are only partially effective; capture bias persists through foreground-only image features. The lack of in situ images (field backgrounds, attached leaves) further limits real-world model transferability [1511.08060, 1604.03169, 2410.22490].

Class imbalance is intrinsic, with healthy samples often dominating (ratio up to 6:1 over minority diseases), especially before augmentation [2601.21307, 2410.22490]. While augmentation and label smoothing partially address this, the scarcity of genuine rare disease samples (e.g., Alternaria, powdery mildew) and the limited per-class test-set cardinality restrict the statistical robustness of evaluation.

## 6. Extensions, Comparative Studies, and Use in Advanced Pipelines

The PlantVillage Apple dataset remains the prototypical reference for classical and modern computer vision approaches in plant pathology. Transfer learning (GoogLeNet, ResNet, EfficientNetV2S, Mamba) consistently outperforms models trained from scratch [1604.03169, 2304.06520, 2601.21307]. Recent work also demonstrates the viability of multimodal large language models (LLMs), GPT-4o, for disease classification with fine-tuning achieving 98.12% accuracy on balanced 4-class subsets [2504.20419]. However, zero-shot LLM performance lags, highlighting the importance of minimal supervised adaptation.

The PV-ALE variant provides a more challenging evaluation due to background/lighting complexity and the inclusion of additional diseases. Table: PV and PV-ALE benchmark (ResNet-50):

| Dataset  | Classes | Accuracy (%) | F₁-score (%) |
|----------|---------|--------------|--------------|
| PV-AL    | 4       | 99.58        | 99.63        |
| PV-ALE   | 6       | 99.11        | 97.87        |

Open access is guaranteed via www.plantvillage.org and linked repositories (Kaggle). The data are governed by a CC BY-SA 3.0 license, mandating that derivative models be openly released [1511.08060, 2410.22490].

## 7. Emerging Best Practices and Future Directions

The PlantVillage Apple dataset should not be viewed as a proxy for real-world, in-field plant disease detection. Robust benchmarking necessitates:
- Quantitative bias testing (e.g., pure-background inputs, random devices) prior to model evaluation [2206.04374]
- Consistently reporting per-class metrics, not only accuracy, to capture rare class performance [2304.06520, 1604.03169]
- Augmenting datasets with realistic, cluttered backgrounds; extending taxonomies to capture broader disease spectra [2410.22490]
- Partitioning splits at the specimen (leaf) level, not by individual image, to prevent overfitting [1604.03169]
- Exploring advanced augmentation, synthetic data generation, and domain adaptation for field transferability [2410.22490]

The definitive limitations of the PlantVillage Apple Leaf Disease dataset are its controlled acquisition, narrow disease spectrum, class imbalance, limited background/lighting variation, and the strong capture bias inherent in uniform-background imaging. Nevertheless, it remains a cornerstone for empirical validation in plant disease computer vision, supporting the development and comparison of increasingly advanced, efficient, and generalizable models.

Source: https://www.emergentmind.com/topics/plantvillage-apple-leaf-disease-dataset