The problem of efficient, interactive foreground/background segmentation in still images is of great practical importance in image editing. Classical image segmentation tools use either texture (color) information or edge (contrast) information. GrabCut is an image segmentation method based on optimization by graph-cut, which successfully combines both types of information. OpenCV is a library of programming functions mainly aimed at real-time computer vision, developed by Intel, and now supported by ‘Willow Garage’ and ‘Itseez’.

While the user observes an image containing a desired object embedded in some surrounding, he can draw a rectangle around the wanted object. The algorithm will then segment this object out of the frame and save the result image separately.

Our application performs real-time image segmentation using GrabCut algorithm implemented in OpenCV open source code. The application itself is implemented with Microsoft Visual Studio.