This repository is a structured archive of my explorations in **Pattern Recognition**.
It covers foundational techniques in image analysis and dimensionality reduction, along with practical implementations from scratch in Python.
The repository is organized by topic, with each notebook focusing on a specific concept.
Current contents include:
- Edge Detection – Basic techniques to detect edges in images.
- Canny Edge Detection – Multi-stage edge detection algorithm with noise reduction.
- Boundary Detection using Contour Tracing – Identifying object boundaries in binary images.
- Principal Component Analysis (PCA) – Dimensionality reduction for high-dimensional datasets.
- Linear Discriminant Analysis (LDA) – Supervised dimensionality reduction and classification.
Additional files include sample images, outputs, and supporting visuals for experiments.
The goal of this repository is to:
- Recreate fundamental pattern recognition algorithms from scratch.
- Understand why and how each technique works.
- Build a reference that connects theory with practical implementations.
This serves as a resource for myself and others who want a hands-on approach to mastering pattern recognition.
- Python
- NumPy
- OpenCV
- Matplotlib
- Jupyter Notebooks
- Clone the repository.
- Navigate to the notebook corresponding to the topic you want to learn.
- Each notebook is well-commented and includes step-by-step code.
- Experiment with different parameters and images to deepen understanding.
More methods (like clustering, classification, and advanced feature extraction) will be added as the project grows.