1996
@mastersthesis{Min1996,
vgclass = {thesis},
vgproject = {cbir},
author = {Thomas Minka},
title = {An Image Database Browser that Learns from User
Interaction},
school = {MIT Media Laboratory},
address = {20 Ames St., Cambridge, MA 02139},
year = {1996},
url = {ftp://whitechapel.media.mit.edu/pub/tech-reports/TR-365.ps.Z},
abstract = {Digital libraries of images and video are rapidly growing
in size and availability. To avoid the expense and limitations of text,
there is considerable interest in navigation by perceptual and other
automatically extractable attributes. Unfortunately, the relevance of
an attribute for a query is not always obvious. Queries which go beyond
explicit color, shape, and positional cues must incorporate multiple
features in complex ways. This dissertation uses machine learning to
automatically select and combine features to satisfy a query, based on
positive and negative examples from the user. The learning algorithm
does not just learn during the course of one session: it learns
continuously, across sessions. The learner improves its learning
ability by dynamically modifying its inductive bias, based on
experience over multiple sessions. Experiments demonstrate the ability
to assist image classification, segmentation, and annotation (labeling
of image regions). The common theme of this work, applied to computer
vision, database retrieval, and machine learning, is building in enough
flexibility to allow adaptation to changing goals.},
}