Good and bad classification of Fresh CARROT

Dataset Description: Carrot (Daucus carota) Classification

1. Overview

This dataset consists of images of good and bad carrots collected for classification purposes. The dataset aims to support machine learning models in distinguishing between high-quality (good) and defective (bad) carrots based on visual attributes.

2. Data Collection Method

Sample Size: Over 500 carrots (both good and bad).

Imaging Device: Realme 11x mobile camera.

Lighting Condition: Natural daylight.

Background: Black, ensuring clear contrast between the carrot and its surroundings.

Image Orientation: Carrots placed in a consistent manner to maintain uniformity across the dataset.

3. Classification Criteria

Good Carrots:

Smooth and firm surface.

Uniform color (bright orange without discoloration).

No visible cracks, mold, or deformities.

Proper shape (not overly twisted or misshapen).

Bad Carrots:

Surface irregularities (cracks, bruises, or mold).

Discoloration (dark spots, pale or green patches).

Deformed or forked shapes.

Signs of wilting or shriveling.

4. Potential Applications

Machine learning-based quality control in agriculture and food industries.

Automated sorting of carrots in packaging units.

Research on visual classification techniques in agricultural produce.

Would you like me to include additional details, such as image resolution or preprocessing techniques