mcanthony/imagesegmentation

Perform image segmentation and background removal in javascript using canvas element and computer vision superpixel algorithms, and convnetjs (experimental)

Image Eraser by Akshay Bhat

http://eraseimage.com/ Image Eraser allows users to perform image segmentation inside browser using a vector editor (FabricJS) and JS implementations of superpixel algorithms.

Very early experimental results using ConvnetJS (ordinary NN not deep net) and support for Zoom In/Out using scrollwheel/touchpad at http://www.eraseimage.com/Experiment

Using SLIC superpixels

Pixelwise prediction using ConvnetJS (with Zoom support)

Following libraries & templates are used:

1. https://almsaeedstudio.com/
2. https://github.com/kyamagu/js-segment-annotator/blob/master/LICENSE
3. http://fabricjs.com/kitchensink/
4. http://inspirit.github.io/jsfeat/
5. http://linkedin.github.io/hopscotch/
6. https://github.com/karpathy/convnetjs
7. http://ace.c9.io/
8. https://github.com/axemclion/seamcarving

License:
Copyright 2015, Cornell University. All Rights Reserved.