Skip to content

Latest commit

 

History

History
67 lines (41 loc) · 2.81 KB

README.md

File metadata and controls

67 lines (41 loc) · 2.81 KB
Raw

Image Processing and Computer Vision Projects

This repository contains five projects exploring fundamental concepts in image processing and computer vision. Each project focuses on a specific topic, with Jupyter Notebook files for code implementation and PDF reports summarizing the project goals, methods, and results.

Project Structure

The repository is structured into five folders, each representing a distinct project:

  • grayscale: Converts color images to grayscale and explores different grayscale conversion techniques.
  • gradient: Calculates and visualizes image gradients for edge detection and feature extraction.
  • filter: Applies various filters to images, including blurring, sharpening, edge detection, and noise reduction.
  • stitch: Implements image stitching algorithms to combine multiple images into a panorama.
  • transformation: Performs various geometric transformations on images, such as rotation, scaling, and translation.

Installation and Running

  1. Install Python and Required Packages: Ensure you have Python 3.x installed. The specific packages needed for each project are listed in the corresponding Jupyter Notebook files.

  2. Open Jupyter Notebooks: Navigate to the respective project folder and open the Jupyter Notebook file (e.g., filter/Filter.ipynb) to run the code and explore the project.

Project Descriptions

1. Grayscale:

This project focuses on converting color images to grayscale:

  • Implementing different grayscale conversion methods (average, luminosity, weighted average).
  • Comparing the results of different methods.
  • Applying grayscale conversion to enhance image features.

2. Filter:

This project demonstrates the application of various image filters to enhance or modify images. It covers:

  • Blurring (Gaussian Blur, Mean Blur)
  • Sharpening (Sobel Operator, Laplacian Operator)
  • Edge Detection (Canny Edge Detection)
  • Noise Reduction (Median Filter)

3. Gradient:

This project explores image gradients and their applications:

  • Calculating gradients using the Sobel operator.
  • Visualizing gradients to identify edges and features.
  • Applying gradient information for image segmentation.

4. Stitch:

This project implements image stitching techniques:

  • Feature detection using SIFT or SURF algorithms.
  • Feature matching to identify corresponding points in different images.
  • Image transformation and blending to create a seamless panorama.

5. Transformation:

This project covers geometric transformations in image processing:

  • Rotation, scaling, and translation of images.
  • Implementing transformations using OpenCV functions.
  • Applying transformations to modify image perspectives or align images.

Contribution

Feel free to contribute to the repository by adding new projects, improving existing code, or suggesting enhancements.