RISE: A Robust Image Search Engine

Debangshu Goswami; Sanjiv K. Bhatia

doi:10.1109/EIT.2006.252181

RISE: A Robust Image Search Engine

Debangshu Goswami, Sanjiv K. Bhatia

University of Missouri-St. Louis

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

Image database indexing is used to improve the efficiency of image retrieval in response to a query expressed as an example image. The query image is processed to extract information that is matched against similar information from images stored in a database to retrieve a set of matched images. The matching process is achieved by a search engine. This paper advances Robust Image Search Engine (RISE). RISE is based on a technique that facilitates content similarity based retrieval of images using an index built on color components of selected blocks of images. It uses a measure of distance between the query and the images in the database. RISE builds on the JPEG indexing algorithm, extending it to formats other than JPEG and into color spaces, in addition to using a relational database. We have implemented RISE as a browser-based search engine, deployed as a java servlet.

Original language	American English
Title of host publication	Pattern Recognition
DOIs	https://doi.org/10.1109/EIT.2006.252181
State	Published - May 1 2006

Disciplines

Library and Information Science
Computer Sciences

Access to Document

10.1109/EIT.2006.252181License: Unspecified

Cite this

@inbook{ab6195d3127c4e95a0d3df06e56a2623,

title = "RISE: A Robust Image Search Engine",

abstract = " Image database indexing is used to improve the efficiency of image retrieval in response to a query expressed as an example image. The query image is processed to extract information that is matched against similar information from images stored in a database to retrieve a set of matched images. The matching process is achieved by a search engine. This paper advances Robust Image Search Engine (RISE). RISE is based on a technique that facilitates content similarity based retrieval of images using an index built on color components of selected blocks of images. It uses a measure of distance between the query and the images in the database. RISE builds on the JPEG indexing algorithm, extending it to formats other than JPEG and into color spaces, in addition to using a relational database. We have implemented RISE as a browser-based search engine, deployed as a java servlet.",

author = "Debangshu Goswami and Bhatia, {Sanjiv K.}",

year = "2006",

month = may,

day = "1",

doi = "10.1109/EIT.2006.252181",

language = "American English",

booktitle = "Pattern Recognition",

}

TY - CHAP

T1 - RISE: A Robust Image Search Engine

AU - Goswami, Debangshu

AU - Bhatia, Sanjiv K.

PY - 2006/5/1

Y1 - 2006/5/1

N2 - Image database indexing is used to improve the efficiency of image retrieval in response to a query expressed as an example image. The query image is processed to extract information that is matched against similar information from images stored in a database to retrieve a set of matched images. The matching process is achieved by a search engine. This paper advances Robust Image Search Engine (RISE). RISE is based on a technique that facilitates content similarity based retrieval of images using an index built on color components of selected blocks of images. It uses a measure of distance between the query and the images in the database. RISE builds on the JPEG indexing algorithm, extending it to formats other than JPEG and into color spaces, in addition to using a relational database. We have implemented RISE as a browser-based search engine, deployed as a java servlet.

AB - Image database indexing is used to improve the efficiency of image retrieval in response to a query expressed as an example image. The query image is processed to extract information that is matched against similar information from images stored in a database to retrieve a set of matched images. The matching process is achieved by a search engine. This paper advances Robust Image Search Engine (RISE). RISE is based on a technique that facilitates content similarity based retrieval of images using an index built on color components of selected blocks of images. It uses a measure of distance between the query and the images in the database. RISE builds on the JPEG indexing algorithm, extending it to formats other than JPEG and into color spaces, in addition to using a relational database. We have implemented RISE as a browser-based search engine, deployed as a java servlet.

UR - http://www.cs.umsl.edu/~sanjiv/publications/2006/01-rise/rise_eit06.pdf

U2 - 10.1109/EIT.2006.252181

DO - 10.1109/EIT.2006.252181

M3 - Chapter

BT - Pattern Recognition

ER -

RISE: A Robust Image Search Engine

Abstract

Disciplines

Access to Document

Other files and links

Cite this