Object categorization from image search: Difference between revisions

Revision as of 05:43, 16 December 2011

Revision as of 23:16, 14 August 2013

Line 13:

== Challenges ==

=== Unrelated images ===

One problem with using Internet image search results as a training set for a classifier is the high percentage of unrelated images within the results. It has been estimated that, when a search engine such as Google images is queried with the name of an object category (such as airplane?, up to 85% of the returned images are unrelated to the category.<ref name = "fergus"/>

Line 20 ⟶ 21:

== pLSA approach ==

In a 2005 paper by Fergus et al.,<ref name = "fergus"/>, [[pLSA]] (probabilistic latent semantic analysis) and extensions of this model were applied to the problem of object categorization from image search. pLSA was originally developed for [[document classification]], but has since been applied to [[computer vision]]. It makes the assumption that images are documents that fit the [[bag of words model]].

=== Model ===

Line 42 ⟶ 43:

=== Application ===

==== ABS-pLSA ====

Absolute position pLSA (ABS-pLSA) attaches ___location information to each visual word by localizing it to one of X 揵ins?in the image. Here, <math>\displaystyle x</math> represents which of the bins the visual word falls into. The new equation is:

Line 59 ⟶ 61:

=== Implementation ===

==== Selecting words ====

Words in an image were selected using 4 different feature detectors:<ref name = "fergus"/>

Line 117 ⟶ 120:

=== Implementation ===

==== Initialization ====

The dataset must be initialized, or seeded with an original batch of images which serve as good exemplars of the object category to be learned. These can be gathered automatically, using the first page or so of images returned by the search engine (which tend to be better than the subsequent images). Alternatively, the initial images can be gathered by hand.

Line 185 ⟶ 189:

| url = http://portal.acm.org/citation.cfm?id=1101838

}}</ref>

== References ==

<references/>

Line 190 ⟶ 195:

== External links ==

{{Empty section|date=July 2010}}

== See also ==

* [[Probabilistic latent semantic analysis]]