📸 Vision Image Processing Pipeline

A modular computer vision pipeline implemented in Python, demonstrating classical image processing techniques using OpenCV and NumPy. This project is designed to process raw images through a customizable sequence of transformations to reduce noise, enhance contrast, and extract structural features.

🚀 Features

• Noise Reduction: Selectable Gaussian, Median, and Bilateral filtering techniques.
• Contrast Enhancement: Global Histogram Equalization and Adaptive Equalization (CLAHE).
• Feature Extraction: High-performance Canny edge detection for boundary identification.
• Configurable Pipeline: Easy-to-tune hyperparameters via a central config.yaml and CLI overrides.

🔄 System Architecture

The image processing flow follows a sequential design, representing a fundamental preprocessing stage for advanced CV systems:

Input Image → Denoising → Contrast Enhancement → Edge Detection → Visualization & Export

⚙️ Installation

1. Clone the repository:

   git clone https://github.com/nguyenpd-vincent/VisionFlow.git
   cd VisionFlow

2. Create and activate a virtual environment (Recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows use: venv\Scripts\activate

3. Install dependencies:

   pip install -r requirements.txt

▶️ Usage

Run the pipeline using the default configuration file:

python main.py --config config.yaml

Process a specific image on the fly via the CLI:

python main.py --image resources/sample.jpg

Run test:

.venv/bin/pip install pytest && .venv/bin/pytest tests  

Output:
The script displays a side-by-side visual comparison and saves processed images (denoised, enhanced, and edge-extracted) to the results/ directory.

📁 Project Structure

vision-image-processing/
├── src/
│   ├── pipeline.py       # Orchestration logic
│   ├── filters.py        # Noise reduction implementations
│   ├── histogram.py      # Contrast enhancement operations
│   └── edge.py           # Feature extraction
├── resources/            # Sample inputs
├── results/              # Processed outputs
├── main.py               # Application entry point
├── config.yaml           # Pipeline hyperparameters
└── requirements.txt      # Project dependencies