Pixel cuts is a basic javascript image processing library that also offers some computer vision functionality. It allows simple matrix and vector manipulation to be done, that is mainly used for the realisation of computer vision algorithms.

The main algorithm that is being implemented is graph cuts. Graph cuts is a semi automatic segmentation technique where an image is represented as a graph and color information is used to assign weights to the edges. The weights are assigned in such a way so that neighbouring pixels with similar color remain together and pixels whose color values differe greatly are separated.

For more information on image filters see image processing. For more information on graph cuts see graph cuts. You can also follow the project on github.

A browser that supports the canvas API is required.

Graph cuts can be used only for research purposes. If you wish to use the graph-cuts for commercial purposes, you should be aware that there is a patent.

For the image filters only non commercial use is allowed.

This project is being implemented and maintained by sotiris gkountelitsas