Image Retrieval ACM 2008
<p>Jul 2, 2008 9:36 PM
 
ACM Computing Surveys, Vol. 40, No. 2, Article 5, Publication date: April 2008.
 
 
Content-Based Image Retrieval CBIR  annotation  computer vision  image processing
 
Image Retrieval: Ideas, Influences, and Trends of the New Age
RITENDRA DATTA, DHIRAJ JOSHI, JIA LI, and JAMES Z. WANG
 
Content-based image retrieval (CBIR), as we see it today, is any technology that
in principle helps to organize digital picture archives by their visual content
 
we also see people from different fields, such as, computer vision, machine
learning, information retrieval, human-computer interaction, database systems, Web
and data mining, information theory, statistics, and psychology contributing and becoming
part of the CBIR community
 
FLICKR
 
Scientific American  Mirsky 2006
 
Their key review article was  Smeulders  et al 2000.
 
The years 1994–2000 can be thought of as the initial phase of research and development
on image retrieval by content. The progress made during this phase was lucidly
summarized at a high level in Smeulders et al. [2000], which has had a clear influence
on progress made in the current decade
 
<b>—Sensory. The sensory gap</b> is the gap between the object in the world and the information
in a (computational) description derived from a recording of that scene.
<b>—Semantic. The semantic gap</b> is the lack of coincidence between the information that
one can extract from the visual data and the interpretation that the same data has
for a user in a given situation.
 
NARROW IMAGE DOMAINS ... just airlines  ailiners.net
 
BROAD image collections  ... high variablity, unpredictability
 
The survey
also lists three broad categories of image search: (1) search by association, where there
is no clear intent at a picture, but instead the search proceeds by iteratively refined
browsing; (2) aimed search, where a specific picture is sought; and (3) category search,
where a single picture representative of a semantic class is sought, for example, to
illustrate a paragraph of text, as introduced in Cox et al. [2000]. Also discussed are different
kinds of domain knowledge that can help reduce the sensory gap in image search.
Notable among them are concepts of syntactic, perceptual, and topological similarity.
The overall goal therefore remains to bridge the semantic and sensorial gaps using
the available visual features of images and relevant domain knowledge to support the
varied search categories, ultimately to satiate the user.
 
extraction of visual content from images is split into two parts, namely
image processing and feature construction
 
Once image features were extracted, the question remained as to how they could be
indexed and matched against each other for retrieval. These methods essentially aimed
to reduce the semantic gap as much as possible, sometimes reducing the sensorial gap
as well in the process. In Smeulders et al. [2000], similarity measures were grouped as
feature-based matching (e.g.,Swain and Ballard [1991]), object-silhouette-based matching
(e.g., Del Bimbo and Pala [1997]), structural feature matching (i.e., hierarchically
ordered sets of features, e.g., Wilson and Hancock [1997]), salient feature matching
(e.g., geometric hashing Wolfson and Rigoutsos [1997]), matching at the semantic level
(e.g., Fagin [1997]), and learning-based approaches for similarity matching (e.g., Wu
et al. [2000] and Webe et al. [2000]). Closely tied to the similarity measures are how
they emulate the user needs, and, more practically, how they can be modified step-wise
with feedback from the user. In this respect, a major advance made in the user interaction
technology for image retrieval was relevance feedback (RF).
 
USER intent:  is user just a BROWSER with no intent
A SURFER with moderate intent or a  ( asurfer might be planning a holiday eg)
SEARCHER with clear and precise intent  (eg trying to find ONE particular image).
 
how large is the database  (eg entire web or your personal collection)
QUERY MODALITY:  keywords,  free text,  an image,  graphics or some composite.
 
<b>—Personal Collection.</b> This consists of a largely homogeneous collection generally small
in size, accessible primarily to its owner, and usually stored on a local storage media.
<b>—Domain-Specific Collection.</b> This is a homogeneous collection providing access to controlled
users with very specific objectives. The collection may be large and hosted on
distributed storage, depending upon the domain. Examples of such a collection are
biomedical and satellite image databases.
<b>—Enterprise Collection.</b> We define this as a heterogeneous collection of pictures accessible
to users within an organization’s intranet. Pictures may be stored in many different
locations. Access may be uniform or nonuniform, depending upon the Intranet
design.
<b>—Archives.</b> These are usually of historical interest and contain large volumes of structured
or semi-structured homogeneous data pertaining to specific topics. Archives
may be accessible to most people on the Internet, with some control of usage. Data is
usually stored in multiple disks or large disk arrays.
—Web.WorldWideWeb pictures are accessible to practically everyone with an Internet
connection. Current WWW image search engines such as Google and Yahoo! images
have a key crawler component which regularly updates their local database to reflect
on the dynamic nature of the Web. Image collection is semi-structured, nonhomogeneous,
and massive in volume, and is usually stored in large disk arrays.
An image retrieval system designed to serve a personal collection should focus on features
such as personalization, flexibility of browsing, and display methodology. For
example, <b>Google’s Picasa system [Picasa 2004] provides a chronological display of images
taking a user on a journey down memory lan</b>e  PICASSA !!!!!!!!!!!!
 
 
 
 
 
 
 
 
 </p>