Logo image
Semantics-Preserving Warping for Stereoscopic Image Retargeting
Book chapter   Peer reviewed

Semantics-Preserving Warping for Stereoscopic Image Retargeting

Chun-Hau Tan, Md Baharul Islam, Lai-Kuan Wong and Kok-Lim Low
IMAGE AND VIDEO TECHNOLOGY, PSIVT 2015, Vol.9431, pp.257-268
Lecture Notes in Computer Science, Springer Nature
01-01-2016

Abstract

Computer Science, Artificial Intelligence Computer Science, Information Systems Computer Science, Theory & Methods Science & Technology Computer Science Technology
Due to availability and popularity of stereoscopic displays in the recent years, research into stereo image retargeting is receiving considerable attention. In this paper, we extend the tearable image warping method for stereo image retargeting. Our method retargets both the left and right image of the stereo image pair simultaneously to preserve scene consistency, and minimize distortion using a global optimization algorithm. It is also able to preserve stereoscopic properties of the resulting stereo image. Experimental results show that our approach can preserve the global image context better than stereoscopic cropping, preserve structural details better than stereoscopic seam carving, and protect objects better than stereoscopic traditional warping. Besides, compared to scene warping, our approach can guarantee semantic connectedness.
url
Link to publisher.View

Related links

Metrics

15 Record Views

Details

Logo image