Interactive image segmentation on mobile devices with touch screen

• Main Author: Ng, Amelia Wan Ting
• Other Authors: Cai Jianfei
• Format: Final Year Project
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
• Online Access: http://hdl.handle.net/10356/59213
• Institution: Nanyang Technological University

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).