Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tobybreckon/correlation-ga
A C++ Teaching Example for a Genetic Algorithm (GA) based on Image Correlation
https://github.com/tobybreckon/correlation-ga
correlation genetic-algorithm opencv
Last synced: 18 days ago
JSON representation
A C++ Teaching Example for a Genetic Algorithm (GA) based on Image Correlation
- Host: GitHub
- URL: https://github.com/tobybreckon/correlation-ga
- Owner: tobybreckon
- License: lgpl-3.0
- Created: 2018-03-24T17:48:32.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2020-08-18T23:14:22.000Z (about 4 years ago)
- Last Synced: 2024-10-07T22:41:13.314Z (about 1 month ago)
- Topics: correlation, genetic-algorithm, opencv
- Language: C++
- Homepage:
- Size: 14.6 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# C++ Genetic Algorithm - Teaching Example
A Genetic Algorithm (GA) example based on using correlation of a selected image region against all other regions in the image to find the location of selection.
Implemented as a C++ header class (_ga.h_) with an interface (_ga_interface.cpp_) to allow for variable population size (P), mutation (M) and cross-over (C) probability settings.
Illustrates all of the key elements of a GA approach including:
- **genes / phenotypes**: _(xi,yi)_ locations of image regions (i.e. chromosomes / genetic representation)
- **population**: random set of _(X x Y)_ dimension regions from the image each at _(xi,yi)_.
- **fitness function**: correlation between mouse selected (click and drag) image region and each region in the population.
- **selection**: fitness proportional selection, roulette wheel.
- **cross-over**: uniform cross-over based on crossing _xi_ and _yi_ co-ordinates between two selected regions.
- **mutation**: randomly perturb bit-pattern of _xi_ and _yi_ co-ordinates of each region in the population.
-- within a readily adaptable C++ class structure.
Requires [OpenCV](http://www.opencv.org) - all tested with OpenCV 2.4.x / 3.x and GCC (Linux) and known to work with MS Visual Studio 20xx on Win32 / Win64.
Example video (click to watch):
[](http://www.youtube.com/watch?v=7cjkJ7xa84Q)
---
### Background:
If I taught you between 2010 and 2013 at [Cranfield University](http://www.cranfield.ac.uk) or [ESTIA](http://www.estia.fr) - this is the C++ GA example from class.
Demo source code is provided _"as is"_ to aid your learning and understanding.
---
### How to download and run:
Download each file as needed or to download the entire repository and run each try:
```
git clone https://github.com/tobybreckon/correlation-ga.git
cd correlation-ga
cmake .
make
./correlation_ga
< use sliders to select population size (P), mutation (M) and cross-over (C) probability settings >
< use mouse to click/drag to select image region >
< hold down - x key to exit / r key to reset >
```
The GA example runs with a webcam connected or from a command line supplied video file of a format OpenCV supports on your system (otherwise edit the code to provide your own image source).
_N.B._ you may need to change the line near the top that specifies the camera device to use on this example - change "0" if you have one webcam, I have to set to "1" to skip my built-in laptop webcam and use the connected USB camera.
---
If referencing this example in your own work please use:
```
@TechReport{breckon2010,
author = {Breckon, T.P. and Barnes, S.E.},
title = {Machine Learning - MSc Course Notes},
institution = {Cranfield University},
year = {2010},
address = {Bedfordshire, UK},
}
```
---
If you find any bugs please raise an issue (or better still submit a pull request, please) - [email protected]
_"may the source be with you"_ - anon.