2004
@article{XST2004,
vgclass = {refpap},
author = {Yaowu Xu and Eli Saber and Tekalp, A. Murat},
title = {Dynamic learning from multiple examples for semantic
object segmentation and search},
journal = {Computer Vision and Image Understanding},
volume = {95},
number = {3},
pages = {334--353},
month = {September},
year = {2004},
url = {http://dx.doi.org/10.1016/j.cviu.2004.04.003},
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. The proposed dynamic learning procedure utilizes
multiple example object templates to improve the accuracy of existing
object segmentations and labels. Multiple example templates may be
images of the same object from different viewing angles, or images of
related objects. This paper also introduces a new shape similarity
metric called normalized area of symmetric differences (NASD), which
has desired properties for use in the proposed ``dynamic learning''
scheme, and is more robust against boundary noise that results from
automatic image segmentation. Performance of the dynamic learning
procedures has been demonstrated by experimental results.},
}