Peanut Quality Images for Visual Inspection, Clean vs Contaminated

A 2-class visual inspection dataset for peanuts, distinguishing clean from contaminated samples. The dataset appears to be designed for computer vision tasks related to food quality control. Its creation details, size, and specific collection methods are not provided in the available metadata.

Use Cases

• Train a binary image classifier to detect contaminated peanuts based on visual features.
• Benchmark computer vision models for automated food quality inspection systems.
• Develop visual inspection algorithms for agricultural sorting and grading tasks.

Strengths

• Focuses on a specific binary classification task (clean vs contaminated), which simplifies model development.
• The dataset is described as adhering to an SNI standard, suggesting a defined quality benchmark.

Limitations

• Row count and dataset size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Kaggle