Interactive image segmentation on mobile devices with touch screen

Image segmentation is one of the most fundamental and challenging problems in image processing. One of the popular applications is to extract the foreground object from the background of an image based on user-defined scribbles. This paper presents a description of three popular image segmentation t...

Full description

Bibliographic Details
Main Author: Ng, Amelia Wan Ting
Other Authors: Cai Jianfei
Format: Final Year Project (FYP)
Language:English
Published: 2014
Subjects:
Online Access:http://hdl.handle.net/10356/59213
Description
Summary:Image segmentation is one of the most fundamental and challenging problems in image processing. One of the popular applications is to extract the foreground object from the background of an image based on user-defined scribbles. This paper presents a description of three popular image segmentation techniques, Geodesic segmentation algorithm, GrabCut algorithm and Random walks segmentation scheme. These algorithms have been successfully implemented on computer platforms. However, there is no such image segmentation algorithm being implemented on mobile devices at current. To keep up with the smart phone and tablet trends, this paper discusses the implementation of image segmentation on touch screen devices whereby users can provide scribbles interactively. The application will focus on the implementation of Geodesic algorithm running on Android Operating System (OS).