Welcome to my Computer Vision Projects Portfolio! This repository showcases a collection of projects demonstrating various computer vision techniques and algorithms. Each project focuses on different aspects of image processing and analysis, providing a comprehensive overview of my skills and knowledge in the field.
This project implements the Canny edge detection algorithm along with additional image processing techniques like the Hough transform.
Key Features:
- Canny edge detection algorithm
- Gaussian smoothing
- Gradient calculation
- Non-maximum suppression
- Double thresholding
- Edge tracking by hysteresis
- Hough transform for line detection
A collection of Python functions for basic image processing operations, focusing on convolution and cross-correlation techniques.
Key Features:
- Naive and optimized 2D convolution implementations
- Zero-padding for images
- Zero-mean cross-correlation
This project implements facial detection and analysis using computer vision techniques, including HOG feature extraction and sliding window detection.
Key Features:
- HOG feature extraction from facial images
- Sliding window detection for face localization
- Image pyramid implementation for multi-scale detection
- Visualization tools for displaying results
An implementation of a panorama image stitching algorithm using various computer vision techniques.
Key Features:
- Harris corner detection
- Feature description (Simple descriptor and HOG)
- Feature matching
- RANSAC for robust estimation of affine transformation
- Image warping and blending
This project focuses on optical flow and feature tracking algorithms, primarily the Lucas-Kanade method and its variations.
Key Features:
- Lucas-Kanade optical flow algorithm
- Iterative and pyramidal Lucas-Kanade methods
- Feature detection using Harris corner detector
- Feature tracking across multiple frames
- Simple object tracking implementation
- Python
- NumPy
- scikit-image
- Matplotlib
- SciPy
- IPython (for some visualizations)
If you have any questions about these projects or would like to discuss potential opportunities, please feel free to contact me at [Your Email Address].
Thank you for visiting my Computer Vision Projects Portfolio!