8000 GitHub - lambertwx/imagetile: Takes a set of images and variably-shaped ROI masks, extracts the masked regions into rectangular tiles, and assembles the tiles into one image. Useful for visualizing training examples that come from lots of images.
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Takes a set of images and variably-shaped ROI masks, extracts the masked regions into rectangular tiles, and assembles the tiles into one image. Useful for visualizing training examples that come from lots of images.

License

Notifications You must be signed in to change notification settings

lambertwx/imagetile

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

imagetile

Takes a set of images and variably-shaped ROI masks, extracts the masked regions into rectangular tiles, and assembles into one image. Useful for visualizing training examples that come from lots of images.

Requirements

Python 3.5+

pillow - Python Imaging Library

scikit-image

rectpack - 2D-bin packing library. Obtain via pip install rectpack, or from https://github.com/secnot/rectpack/ .

Basic Usage

Extract the tiles from each of your images and masks.

tiles = extracttiles(img1, mask1, 5)
tiles.extend(extracttiles(img2, mask2, 5))

Then call layouttiles to arrange the tiles into a nice mosaic using 2D bin packing.

mosaic = layouttiles(tiles)

About

Takes a set of images and variably-shaped ROI masks, extracts the masked regions into rectangular tiles, and assembles the tiles into one image. Useful for visualizing training examples that come from lots of images.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

0