papaya curry

Papaya Curry Classification Dataset Description

1. Overview

The dataset consists of over 500 images of papaya curry (Carica papaya), classified into two categories: good and bad. The primary goal is to develop an automated classification model that distinguishes between high-quality and defective papaya curry based on visual characteristics.

2. Data Collection

Camera Used: Redmi 9 Power

Lighting Conditions: Natural daylight

Background: White

Total Samples: 500+

Classification Categories:

Good Papaya Curry: Fresh, well-cooked, properly textured, and visually appealing curry with appropriate color and consistency.

Bad Papaya Curry: Overcooked, undercooked, spoiled, discolored, watery, or containing unwanted particles.

3. Image Properties

Resolution: Varies based on the Redmi 9 Power’s camera settings (typically 48 MP for high-quality images).

File Format: Likely JPEG or PNG

Angle & Focus: Close-up shots focusing on texture, color, and consistency.

4. Features for Classification

Color Variations: Fresh papaya curry appears vibrant orange-yellow, whereas bad samples may show dark spots, excessive oil separation, or an unnatural hue.

Texture & Consistency: Good curry has a smooth, uniform consistency, while bad curry may appear lumpy, watery, or excessively dry.

Presence of Spoilage: Indicators like mold, excessive oil separation, or unnatural glossiness may signify a bad sample.

Foreign Particles: Contamination by burnt elements or external particles can impact classification.

5. Potential Applications

Quality control in food processing.

AI-based food safety assessment.

Automated inspection systems for restaurants and food suppliers.

This dataset provides a structured approach for training machine learning models to distinguish between good and bad papaya curry, ensuring improved food quality assessment.