Title :
Scribble2focus: An interactive photo refocusing system based on mobile stereo imaging
Author :
Vu, Dung T. ; Chidester, Benjamin ; Jiangbo Lu ; Do, Minh N.
Author_Institution :
ADSC Illinois at Singapore, Singapore, Singapore
Abstract :
This paper proposes a novel, depth-based image refocusing system for mobile devices equipped with stereo cameras, called Scribble2focus. The system provides a simple and intuitive interface, which allows the user to refocus the image by indicating an object of interest with a simple finger stroke. A stereo matching algorithm based on a Minimum Spanning Tree approach is proposed to infer depth from images from the stereo cameras. Using the depth information and a thin lens model, input all-focus images are synthetically refocused. Experiments show that the proposed system produces quality refocusing results with minimal computational requirements. The system requires only around 1.5 seconds to process a pair of 640×360 images in the off-line step, making it possible for future deployment on a mobile device.
Keywords :
image matching; image sensors; interactive systems; mobile computing; stereo image processing; trees (mathematics); depth information; depth-based image refocusing system; finger stroke; interactive photo refocusing system; minimum spanning tree approach; mobile devices; mobile stereo imaging; scribble2focus; stereo cameras; stereo matching algorithm; thin lens model; Cameras; Estimation; Lenses; Mobile communication; Mobile handsets; Rendering (computer graphics); Stereo vision;
Conference_Titel :
Global Conference on Signal and Information Processing (GlobalSIP), 2013 IEEE
Conference_Location :
Austin, TX
DOI :
10.1109/GlobalSIP.2013.6737001