Semantic object segmentation by dynamic learning from multiple examples. Xu, Y., Saber, E, & Tekalp, A. In 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL III, PROCEEDINGS: IMAGE AND MULTIDIMENSIONAL SIGNAL PROCESSING SPECIAL SESSIONS, pages 561-564, 2004. IEEE Signal Proc Soc; IEEE. IEEE International Conference on Acoustics, Speech, and Signal Processing, Montreal, CANADA, MAY 17-21, 2004
abstract   bibtex   
We present a novel ``dynamic learning'' approach for an intelligent image database system to automatically improve object segmentation and labeling without user intervention, as new examples become available, for object-based indexing. The proposed approach is an extension of our earlier work on ``learning by example,'' which addressed labeling of similar objects in a set of database images based on a single example [1]. It utilizes multiple example object templates to improve the accuracy of existing object segmentations and labels. We also propose to use Normalized Area of Symmetric Differences (NASD) as the similarity metric in ``dynamic learning'', due to its robustness to boundary noise that results from automatic image segmentation. The performance of the dynamic learning concept is demonstrated by experimental results.
@inproceedings{ ISI:000222177700141,
Author = {Xu, YW and Saber, E and Tekalp, AM},
Book-Group-Author = {{IEEE}},
Title = {{Semantic object segmentation by dynamic learning from multiple examples}},
Booktitle = {{2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL
   PROCESSING, VOL III, PROCEEDINGS: IMAGE AND MULTIDIMENSIONAL SIGNAL
   PROCESSING SPECIAL SESSIONS}},
Year = {{2004}},
Pages = {{561-564}},
Note = {{IEEE International Conference on Acoustics, Speech, and Signal
   Processing, Montreal, CANADA, MAY 17-21, 2004}},
Organization = {{IEEE Signal Proc Soc; IEEE}},
Abstract = {{We present a novel ``dynamic learning{''} approach for an intelligent
   image database system to automatically improve object segmentation and
   labeling without user intervention, as new examples become available,
   for object-based indexing. The proposed approach is an extension of our
   earlier work on ``learning by example,{''} which addressed labeling of
   similar objects in a set of database images based on a single example
   {[}1]. It utilizes multiple example object templates to improve the
   accuracy of existing object segmentations and labels. We also propose to
   use Normalized Area of Symmetric Differences (NASD) as the similarity
   metric in ``dynamic learning{''}, due to its robustness to boundary
   noise that results from automatic image segmentation. The performance of
   the dynamic learning concept is demonstrated by experimental results.}},
Unique-ID = {{ISI:000222177700141}},
}

Downloads: 0