An engaging course repository for computer vision assignments, focusing on practical implementation of image processing, feature detection, object recognition, and deep learning techniques using Python and OpenCV.
- Basic Operations
- Image manipulation
- Color space conversions
- Filtering techniques
- Histogram analysis
- Advanced Techniques
- Edge detection
- Morphological operations
- Image enhancement
- Frequency domain processing
- Feature Extraction
- SIFT/SURF implementations
- Corner detection
- Blob detection
- Template matching
- Pattern Recognition
- Feature matching
- Object detection
- Face recognition
- Scene classification
- Neural Networks
- CNN architectures
- Transfer learning
- Model training
- Performance optimization
- Modern Architectures
- ResNet
- YOLO
- U-Net
- Transformers
- Python Environment
- Python 3.9+
- pip or conda
- Virtual environment
- Git
- Required Libraries
- OpenCV 4.8+
- NumPy 1.21+
- PyTorch 2.0+
- Matplotlib 3.5+
# requirements.txt
opencv-python>=4.8.0
numpy>=1.21.0
torch>=2.0.0
matplotlib>=3.5.0
scikit-image>=0.19.0
pillow>=9.0.0
jupyter>=1.0.0# Clone the repository
git clone https://github.com/university/cv-course.git
cd cv-course
# Create virtual environment
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Verify installation
python -c "import cv2; print(cv2.__version__)"| Component | Weight | Description |
|---|---|---|
| Implementation | Code correctness & efficiency |
| Results | Output quality & analysis |
- Follow PEP 8 style guide
- Document all functions
- Include unit tests
- Maintain clean commit history
Last Updated: February 2025