Fresh and Rotten Vegetable Images for Classification

Cleaned image dataset for distinguishing fresh from rotten vegetables. The collection has had duplicate images removed, which suggests a focus on data quality for model training. The dataset's origin, size, and specific vegetable types are not detailed in the provided metadata.

Use Cases

• Train a binary classifier to detect fresh vs. rotten produce based on image data.
• Develop a multi-class classifier to identify specific types of rotten vegetables.
• Benchmark model performance on a cleaned dataset where duplicate images have been removed.
• Fine-tune pre-trained convolutional neural networks (CNNs) for agricultural computer vision tasks.

Strengths

• Dataset has been cleaned with duplicate images removed, which can reduce bias in model training.
• Platform tags indicate it is intended for deep learning and CNN applications.

Limitations

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

Provenance

Source

Kaggle