Welcome to my Computer Vision (CV) Experiments repository.
This repo will contain all of my small projects, studies, and practical exercises as I learn and explore the field of Computer Vision. Each folder will represent a separate experiment or topic — from basic image manipulation to advanced vision algorithms.
Computer Vision is one of the fastest-growing areas in AI, enabling machines to interpret and understand visual information from the world.
It allows computers to:
- Detect objects
- Recognize faces
- Understand scenes
- Track movement
- Make intelligent decisions based on images or videos
It bridges the gap between digital systems and the physical world, making it foundational in countless applications we rely on every day.
Computer Vision powers technology you encounter constantly:
Used for lane detection, pedestrian recognition, traffic sign reading, depth estimation, etc.
Facial recognition unlock, AR filters, photo enhancement.
MRI analysis, tumor detection, X-ray reading, robotic surgery assistance.
Product recognition, automated checkout, virtual try-on systems.
Person tracking, anomaly detection, security access systems.
Quality control, defect inspection, robotic vision systems.
This repository will include experiments such as (and not limited to):
- Basic image loading and manipulation
- Color space conversions
- Grayscale transformation
- Image filtering and smoothing
- Edge detection & feature extraction
- Histograms and thresholding
- Morphological operations
- Object detection basics
- Image segmentation
- Practical mini-projects (OCR, face detection, etc.)
Each experiment folder will contain:
- A standalone README
- Python code
- Example images
- Brief explanation of the concepts
- Clone the repo:
git clone <repository-url>
cd <repository-folder>- Per-experiment setup (typically):
- Create a Python virtual environment (e.g.,
python -m venv .venv) - Install packages from
requirements.txt(e.g.,pip install -r requirements.txt) - Run the experiment script (for example:
python main.pyinside an experiment folder)
- Explore experiments in order or jump to topics that interest you.
Computer Vision techniques are commonly grouped into three categories:
- Canny edge detection
- Sobel filters
- Thresholding and histograms
- Morphological operations (erosion, dilation)
- Contours and Hough transforms
- SVMs, k-NN, Random Forests
- Feature descriptors: SIFT, SURF, ORB
- Convolutional Neural Networks (CNNs)
- Object detection (YOLO, Faster R-CNN)
- Semantic segmentation (U-Net, DeepLab)
- Vision Transformers (ViT)
These approaches are complementary: classical methods are lightweight and interpretable, while deep learning provides state-of-the-art performance for many tasks.
The repository provides a structured, hands-on path to:
- Practice CV fundamentals
- Explore real-world use cases
- Build a foundation for advanced AI/ML topics
- Document experiments and learning notes
- Share insights with others
This is primarily a personal learning repository, but suggestions are welcome. Feel free to open an issue or submit a pull request with improvements.
More experiments will be added over time as the repository grows with new topics and implementations.
Happy Learning! 🚀