Object-based Image Retrieval using Local Feature Extraction and Relevance Feedback

This paper addresses the problem of object-based image retrieval, by using local feature extraction and a relevance feedback mechanism for quickly narrowing down the image search process to the user needs. This approach relies on the hypothesis that semantically similar images are clustered in some...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer applications 2013-01, Vol.78 (7), p.8-14
Main Authors: G Freitas, rio H, C P, vio L, Assis, Guilherme T
Format: Article
Language:English
Subjects:
Feature extraction
Feedback
Mathematical analysis
Query processing
Retrieval
Searching
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 14
container_issue 7
container_start_page 8
container_title International journal of computer applications
container_volume 78
creator G Freitas, rio H
C P, vio L
Assis, Guilherme T
description This paper addresses the problem of object-based image retrieval, by using local feature extraction and a relevance feedback mechanism for quickly narrowing down the image search process to the user needs. This approach relies on the hypothesis that semantically similar images are clustered in some feature space and, in this scenario: (i) computes image signatures that are invariant to scale and rotation using SIFT, (ii) calculates the vector of locally aggregated descriptors (VLAD) to make a fixed length descriptor for the images, (iii) reduce the VLAD descriptor dimensionality with Principal Component Analysis (PCA) and (iv) uses the k-Means algorithm for grouping images that are semantically similar. The proposed approach has been successfully validated using 33,192 images from the ALOI database, obtaining a mean recall value of 47. 4% for searches of images containing objects that are identical to the object query and 20. 7% for searches of images containing different objects (albeit visually similar) to the object query.
doi_str_mv 10.5120/13499-1239
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1464549822</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1464549822</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1329-e1a2a32694473e6891f5e715182e6e18b46a1fc4fbbcad938a7e81323ffbbd713</originalsourceid><addsrcrecordid>eNpd0FFLwzAQB_AgCo65Fz9BwRcRqr0kbZNHGZsOCoOhz-GaXkdn186kFf32Zs4HMS93HL8Lx5-xa0juU-DJAwipdQxc6DM2SXSexkqp_PxPf8lm3u-S8ITmmZYTtlmXO7JDXKKnKlrtcUvRhgbX0Ae20eibbhsVvQ39knAYHUWLz8GhHZq-i7CrAm4D7SwFQFWJ9u2KXdTYepr91il7XS5e5s9xsX5azR-L2ILgOiZAjuJ4hcwFZUpDnVIOKShOGYEqZYZQW1mXpcVKC4U5qbAp6jCpchBTdnv69-D695H8YPaNt9S22FE_egMyk6nUivNAb_7RXT-6LlwXlASd8IzLoO5Oyrree0e1Obhmj-7LQGKOCZufhM0xYfENuiVrig</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1441902624</pqid></control><display><type>article</type><title>Object-based Image Retrieval using Local Feature Extraction and Relevance Feedback</title><source>Freely Accessible Journals</source><creator>G Freitas, rio H ; C P, vio L ; Assis, Guilherme T</creator><creatorcontrib>G Freitas, rio H ; C P, vio L ; Assis, Guilherme T</creatorcontrib><description>This paper addresses the problem of object-based image retrieval, by using local feature extraction and a relevance feedback mechanism for quickly narrowing down the image search process to the user needs. This approach relies on the hypothesis that semantically similar images are clustered in some feature space and, in this scenario: (i) computes image signatures that are invariant to scale and rotation using SIFT, (ii) calculates the vector of locally aggregated descriptors (VLAD) to make a fixed length descriptor for the images, (iii) reduce the VLAD descriptor dimensionality with Principal Component Analysis (PCA) and (iv) uses the k-Means algorithm for grouping images that are semantically similar. The proposed approach has been successfully validated using 33,192 images from the ALOI database, obtaining a mean recall value of 47. 4% for searches of images containing objects that are identical to the object query and 20. 7% for searches of images containing different objects (albeit visually similar) to the object query.</description><identifier>ISSN: 0975-8887</identifier><identifier>EISSN: 0975-8887</identifier><identifier>DOI: 10.5120/13499-1239</identifier><language>eng</language><publisher>New York: Foundation of Computer Science</publisher><subject>Feature extraction ; Feedback ; Mathematical analysis ; Query processing ; Retrieval ; Searching</subject><ispartof>International journal of computer applications, 2013-01, Vol.78 (7), p.8-14</ispartof><rights>Copyright Foundation of Computer Science 2013</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27903,27904</link.rule.ids></links><search><creatorcontrib>G Freitas, rio H</creatorcontrib><creatorcontrib>C P, vio L</creatorcontrib><creatorcontrib>Assis, Guilherme T</creatorcontrib><title>Object-based Image Retrieval using Local Feature Extraction and Relevance Feedback</title><title>International journal of computer applications</title><description>This paper addresses the problem of object-based image retrieval, by using local feature extraction and a relevance feedback mechanism for quickly narrowing down the image search process to the user needs. This approach relies on the hypothesis that semantically similar images are clustered in some feature space and, in this scenario: (i) computes image signatures that are invariant to scale and rotation using SIFT, (ii) calculates the vector of locally aggregated descriptors (VLAD) to make a fixed length descriptor for the images, (iii) reduce the VLAD descriptor dimensionality with Principal Component Analysis (PCA) and (iv) uses the k-Means algorithm for grouping images that are semantically similar. The proposed approach has been successfully validated using 33,192 images from the ALOI database, obtaining a mean recall value of 47. 4% for searches of images containing objects that are identical to the object query and 20. 7% for searches of images containing different objects (albeit visually similar) to the object query.</description><subject>Feature extraction</subject><subject>Feedback</subject><subject>Mathematical analysis</subject><subject>Query processing</subject><subject>Retrieval</subject><subject>Searching</subject><issn>0975-8887</issn><issn>0975-8887</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2013</creationdate><recordtype>article</recordtype><recordid>eNpd0FFLwzAQB_AgCo65Fz9BwRcRqr0kbZNHGZsOCoOhz-GaXkdn186kFf32Zs4HMS93HL8Lx5-xa0juU-DJAwipdQxc6DM2SXSexkqp_PxPf8lm3u-S8ITmmZYTtlmXO7JDXKKnKlrtcUvRhgbX0Ae20eibbhsVvQ39knAYHUWLz8GhHZq-i7CrAm4D7SwFQFWJ9u2KXdTYepr91il7XS5e5s9xsX5azR-L2ILgOiZAjuJ4hcwFZUpDnVIOKShOGYEqZYZQW1mXpcVKC4U5qbAp6jCpchBTdnv69-D695H8YPaNt9S22FE_egMyk6nUivNAb_7RXT-6LlwXlASd8IzLoO5Oyrree0e1Obhmj-7LQGKOCZufhM0xYfENuiVrig</recordid><startdate>20130101</startdate><enddate>20130101</enddate><creator>G Freitas, rio H</creator><creator>C P, vio L</creator><creator>Assis, Guilherme T</creator><general>Foundation of Computer Science</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20130101</creationdate><title>Object-based Image Retrieval using Local Feature Extraction and Relevance Feedback</title><author>G Freitas, rio H ; C P, vio L ; Assis, Guilherme T</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1329-e1a2a32694473e6891f5e715182e6e18b46a1fc4fbbcad938a7e81323ffbbd713</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Feature extraction</topic><topic>Feedback</topic><topic>Mathematical analysis</topic><topic>Query processing</topic><topic>Retrieval</topic><topic>Searching</topic><toplevel>online_resources</toplevel><creatorcontrib>G Freitas, rio H</creatorcontrib><creatorcontrib>C P, vio L</creatorcontrib><creatorcontrib>Assis, Guilherme T</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>International journal of computer applications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>G Freitas, rio H</au><au>C P, vio L</au><au>Assis, Guilherme T</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Object-based Image Retrieval using Local Feature Extraction and Relevance Feedback</atitle><jtitle>International journal of computer applications</jtitle><date>2013-01-01</date><risdate>2013</risdate><volume>78</volume><issue>7</issue><spage>8</spage><epage>14</epage><pages>8-14</pages><issn>0975-8887</issn><eissn>0975-8887</eissn><abstract>This paper addresses the problem of object-based image retrieval, by using local feature extraction and a relevance feedback mechanism for quickly narrowing down the image search process to the user needs. This approach relies on the hypothesis that semantically similar images are clustered in some feature space and, in this scenario: (i) computes image signatures that are invariant to scale and rotation using SIFT, (ii) calculates the vector of locally aggregated descriptors (VLAD) to make a fixed length descriptor for the images, (iii) reduce the VLAD descriptor dimensionality with Principal Component Analysis (PCA) and (iv) uses the k-Means algorithm for grouping images that are semantically similar. The proposed approach has been successfully validated using 33,192 images from the ALOI database, obtaining a mean recall value of 47. 4% for searches of images containing objects that are identical to the object query and 20. 7% for searches of images containing different objects (albeit visually similar) to the object query.</abstract><cop>New York</cop><pub>Foundation of Computer Science</pub><doi>10.5120/13499-1239</doi><tpages>7</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0975-8887
ispartof International journal of computer applications, 2013-01, Vol.78 (7), p.8-14
issn 0975-8887
0975-8887
language eng
recordid cdi_proquest_miscellaneous_1464549822
source Freely Accessible Journals
subjects Feature extraction
Feedback
Mathematical analysis
Query processing
Retrieval
Searching
title Object-based Image Retrieval using Local Feature Extraction and Relevance Feedback
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T03%3A21%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Object-based%20Image%20Retrieval%20using%20Local%20Feature%20Extraction%20and%20Relevance%20Feedback&rft.jtitle=International%20journal%20of%20computer%20applications&rft.au=G%20Freitas,%20rio%20H&rft.date=2013-01-01&rft.volume=78&rft.issue=7&rft.spage=8&rft.epage=14&rft.pages=8-14&rft.issn=0975-8887&rft.eissn=0975-8887&rft_id=info:doi/10.5120/13499-1239&rft_dat=%3Cproquest_cross%3E1464549822%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c1329-e1a2a32694473e6891f5e715182e6e18b46a1fc4fbbcad938a7e81323ffbbd713%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1441902624&rft_id=info:pmid/&rfr_iscdi=true