This project implements an Image Processing Toolbox using PyQt6, designed to provide a comprehensive suite of tools for image analysis and manipulation. The toolbox integrates classical algorithms such as Sobel, Otsu, and Fourier transforms, enabling users to perform tasks like noise simulation, filtering, edge detection, and histogram analysis. The responsive GUI allows for real-time visualization and multi-image comparison, making it suitable for both educational purposes and practical applications in fields like computer vision, medical imaging, and digital photography.
The Mixer Mode allows users to blend two images using frequency-domain manipulation. By adjusting cutoff sliders, users can control the contribution of low and high-frequency components from each image, enabling advanced image fusion techniques. This mode is particularly useful for applications in image stitching and multi-spectral imaging.
| Snapshot | Description |
|---|---|
 |
Blend two images using frequency-domain manipulation with adjustable cutoff sliders. |
The Edge Detection Mode implements classical edge detection algorithms, including Sobel, Prewitt, Roberts, and Canny. These techniques are fundamental in feature extraction and object detection, with applications in autonomous vehicles and robotics.
| Edge Detection Method | Snapshot | Description |
|---|---|---|
| Sobel |  |
Detects edges using gradient approximation. |
| Prewitt |  |
Similar to Sobel but with a different kernel. |
| Roberts |  |
Detects edges using diagonal gradients. |
| Canny |  |
A multi-stage algorithm for optimal edge detection. |
The Noise Mode simulates various types of noise, including Gaussian, Uniform, and Salt & Pepper noise. This mode is essential for understanding how noise impacts image quality and how different filters can mitigate its effects. It is particularly relevant in signal processing and noise reduction research.
| Noise Type | Snapshot | Description |
|---|---|---|
| Gaussian Noise |  |
Simulates additive Gaussian noise, commonly used to model sensor noise. |
| Uniform Noise |  |
Simulates uniform noise, often used in statistical simulations. |
| Salt & Pepper Noise |  |
Simulates impulsive noise, typical in corrupted images. |
The Filter Mode provides tools to apply spatial-domain filters such as Average, Gaussian, and Median filters. These filters are crucial for noise reduction and image smoothing, with applications in medical imaging and computer vision.
| Filter Type | Snapshot | Description |
|---|---|---|
| Average Filter |  |
Applies a simple averaging filter to smooth the image. |
| Gaussian Filter |  |
Applies a Gaussian kernel for noise reduction while preserving edges. |
| Median Filter |  |
Removes salt and pepper noise by replacing each pixel with the median of its neighborhood. |
The Other Modes section includes advanced tools for intensity normalization, thresholding, histogram analysis, and frequency filtering. These tools are essential for image enhancement and feature extraction in machine learning and computer vision pipelines.
| Mode | Snapshot | Description |
|---|---|---|
| Normalization |  |
Normalizes pixel intensities for better contrast. |
| Thresholding |  |
Applies binary thresholding to segment images. |
| Histogram & CDF |  |
Analyzes image histograms and cumulative distribution functions. |
| Frequency Filtering |  |
Applies frequency-domain filters for advanced image manipulation. |
- Install dependencies:
pip install -r requirements.txt
Salah Mohamed |
Ayatullah Ahmed |
Abdelrahman Sayed |
Ahmed Rafaat |