Shelf life determination of Hypophthalmicthys molitrix ( Silver Carp )

This project, titled "Good and Bad Classification of Silver Carp(Hypophthalmichthys molitrix) is designed to develop an image classification system that distinguishes between healthy (good) and unhealthy (bad) Silver Carp fish (Hypophthalmichthys molitrix). The dataset consists of approximately 2000 images, evenly distributed between good and bad samples. All images were captured using a Realme 5i mobile camera, providing high-resolution visual data suitable for machine learning applications. The fish were photographed against a black background in daylight conditions to ensure consistency, clarity, and accurate feature capture.
Dataset Composition
Good Samples (Healthy)
The dataset includes approximately 1000 images of healthy Silver Carp fish. These images show fish with:
Bright, shiny, and intact scales
Clear, transparent eyes
Proper body shape without deformities
Natural coloration and smooth texture
These samples represent the positive class and help train the model to recognize healthy fish conditions.
Bad Samples (Unhealthy)
The dataset also contains approximately 1000 images of unhealthy Silver Carp fish. These fish may exhibit:
Dull or discolored scales
Cloudy or damaged eyes
Physical deformities
Visible injuries or infections
Poor overall physical condition
These images represent the negative class, enabling the model to identify unhealthy fish accurately.
Data Collection Setup
All images were captured using a Realme 5i smartphone camera, known for its reliable image quality and resolution. A black background was used intentionally to:
Enhance contrast between the fish and the background
Reduce noise and unwanted visual distractions
Highlight important visual features such as scales, eyes, and body structure
Images were taken under natural daylight conditions, ensuring consistent illumination and accurate representation of color and texture.
Image Characteristics
The dataset includes variations in:
Fish size
Body orientation
Color intensity
Health condition
This diversity improves the robustness of the machine learning model and ensures better performance in real-world scenarios.
Data Annotation
Each image is carefully labeled as either:
"Good" (Healthy)
"Bad" (Unhealthy)
These labels serve as the ground truth, allowing the machine learning model to learn the differences between healthy and unhealthy fish accurately.