Abstract
Image content analysis is important for automated image organization, labeling, and search. Partitioning an image into meaningful regions is one of the fundamental problems in image analysis. Anaglyph images and videos are more and more popular, such as in Flickr and YouTube. The anaglyph images provide disparity cue in a single image, which could be useful for image analysis. This paper exploits disparity cue for image partition. An image partition method for anaglyph is proposed. The disparity or depth cue is integrated with the traditional single-view image segmentation. A concept called dominant disparity is proposed, corresponding to each single-view image segment, which largely tolerates the disparity errors and image over-segmentations. A cue integration algorithm is developed. The integration is at the level of image segments rather than pixels, and object-level image segmentation is achieved. Experiments on both synthetic and real anaglyph images demonstrate the effectiveness of the proposed image partition method for anaglyph image analysis. To the best of our knowledge, our work is for the first time to perform anaglyph image partition.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Machine Learning and Cybernetics
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
