https://github.com/sunsided/convolution-template-matching

Template Matching by Convolution in MATLAB
https://github.com/sunsided/convolution-template-matching

feature-detection image-processing matlab template-matching

Last synced: 4 months ago
JSON representation

Template Matching by Convolution in MATLAB

• Host: GitHub
• URL: https://github.com/sunsided/convolution-template-matching
• Owner: sunsided
• Created: 2016-08-18T00:22:24.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2016-08-19T14:42:09.000Z (over 8 years ago)
• Last Synced: 2024-10-11T02:31:12.769Z (4 months ago)
• Topics: feature-detection, image-processing, matlab, template-matching
• Language: Matlab
• Size: 325 KB
• Stars: 5
• Watchers: 3
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Template Matching by Convolution

*Template matching* attempts to find instances of a given template in an existing image by finding areas of maximum correspondence. While this can be done in terms of a cross correlation, care has to be taken to normalize both input and template, as cross correlation by itself is not invariant to mean shifts.

This experiment follows the idea that **convolution** is the same operation as **cross correlation**, when all axes of the template (i.e. the kernel) have been flipped; in terms of a two-dimensional correlation with a template, this results in a two-dimensional convolution of the same template, rotated by 180°; so

```matlab

xcorr2(image, template)

```

is conceptually the same as

```matlab

conv2(image, fliplr(flipud(template)) % or

conv2(image, rot90(template, 2))

```

Finding the template matches is then a question of finding the local minima (i.e. areas of maximum correspondence).