Image Segmentation and Matting in Realtime on a Mobile Device
Elad Richardson
Supervised by Anastasia Dubrovina and Aaron Wetzler
Image Segmentation is a known problem in the world of Image Processing, where we try to partition a given image into several different segments that compose the original image. One use of the segmentation process is the separation of an object of interest from the rest of the image. Many algorithms use some form of user input in order to locate a specific object of interest and segment it out, an optional form of user inputs are scribbles, simple lines drawn by the user. The user is usually requested to draw at least one scribble inside the object of the interest and one on the outside, those two scribbles give the algorithm the basic information it needs in order to segment the object of interest from the rest of the image.
In the our project we've implemented a scribble-based algorithm for extracting object from natural photos and pasting them seamlessly into a different background under the constrains of a mobile device computational power. The algorithm was first developed and tested on a personal computer with the help of openCV’s C++ libraries and was then ported to Android using the Native Development Kit. We used the Android Software Development Kit in order to wrap the algorithm in a user friendly interface to create an application that anybody can use.
Please, see project report.
Please, see final presentation.
Please, see CutOut.