Saliency detection based on MI-KSVD

In this paper, we propose a visual saliency detection algorithm with MI-KSVD, a codebook learning algorithm that balances reconstruction error and mutual incoherence of the codebook. We first segment the images into superpixels by simple linear iterative clustering (SLIC), which can improve the effi...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianhao Shen, Jinqing Qi
Format: Conference Proceeding
Language:English
Subjects:
Biological system modeling
Computational modeling
Dictionaries
Encoding
Image reconstruction
Image segmentation
MI-KSVD
multi-scale
object location
Saliency
smoothing
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 30
container_issue
container_start_page 25
container_title
container_volume
creator Tianhao Shen
Jinqing Qi
description In this paper, we propose a visual saliency detection algorithm with MI-KSVD, a codebook learning algorithm that balances reconstruction error and mutual incoherence of the codebook. We first segment the images into superpixels by simple linear iterative clustering (SLIC), which can improve the efficiency and correctness of the progress. Then we calculate the reconstruction errors based on the initial background propagated from the boundaries of the image. We use a weighted sum of multi-scale region-level saliency as the pixel-level saliency in order to generate a more continuous and smooth result. Based on that, we further use object recognition as a vital prior to improve the performance of our method. Experimental results on three benchmark datasets show that the proposed method performed well to reach our expectations in terms of precision and recall.
doi_str_mv 10.1109/ICAwST.2015.7314015
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_7314015</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7314015</ieee_id><sourcerecordid>7314015</sourcerecordid><originalsourceid>FETCH-LOGICAL-i208t-a4e238dd94bba6fa3caef1cd5b020d4291532d1ce103b157152ac95c0443893e3</originalsourceid><addsrcrecordid>eNo9j81Kw0AURkdRsNQ8QTcB14n3zp2_u5SqtVhxkeq2TGZuIFKrNAHp21uwuDpn9XE-pWYINSLw7XJ-99Osaw1oa09ojjxTBfuAxnnyzgZ_riaatK0ss7n49-CuVDEMHwCA7Fg7nqibJm572aVDmWWUNPZfu7KNg-TyKC_L6rl5v79Wl13cDlKcOFVvjw_r-VO1el0cY1ZVryGMVTSiKeTMpm2j6yKlKB2mbFvQkI1mtKQzJkGgFq1Hq2Nim8AYCkxCUzX72-1FZPO97z_j_rA5XaRfcOtA_Q</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Saliency detection based on MI-KSVD</title><source>IEEE Xplore All Conference Series</source><creator>Tianhao Shen ; Jinqing Qi</creator><creatorcontrib>Tianhao Shen ; Jinqing Qi</creatorcontrib><description>In this paper, we propose a visual saliency detection algorithm with MI-KSVD, a codebook learning algorithm that balances reconstruction error and mutual incoherence of the codebook. We first segment the images into superpixels by simple linear iterative clustering (SLIC), which can improve the efficiency and correctness of the progress. Then we calculate the reconstruction errors based on the initial background propagated from the boundaries of the image. We use a weighted sum of multi-scale region-level saliency as the pixel-level saliency in order to generate a more continuous and smooth result. Based on that, we further use object recognition as a vital prior to improve the performance of our method. Experimental results on three benchmark datasets show that the proposed method performed well to reach our expectations in terms of precision and recall.</description><identifier>ISSN: 2325-5986</identifier><identifier>EISSN: 2325-5994</identifier><identifier>EISBN: 9781467376587</identifier><identifier>EISBN: 1467376582</identifier><identifier>DOI: 10.1109/ICAwST.2015.7314015</identifier><language>eng</language><publisher>IEEE</publisher><subject>Biological system modeling ; Computational modeling ; Dictionaries ; Encoding ; Image reconstruction ; Image segmentation ; MI-KSVD ; multi-scale ; object location ; Saliency ; smoothing ; Visualization</subject><ispartof>2015 IEEE 7th International Conference on Awareness Science and Technology (iCAST), 2015, p.25-30</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7314015$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27923,54553,54930</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7314015$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Tianhao Shen</creatorcontrib><creatorcontrib>Jinqing Qi</creatorcontrib><title>Saliency detection based on MI-KSVD</title><title>2015 IEEE 7th International Conference on Awareness Science and Technology (iCAST)</title><addtitle>ICAwST</addtitle><description>In this paper, we propose a visual saliency detection algorithm with MI-KSVD, a codebook learning algorithm that balances reconstruction error and mutual incoherence of the codebook. We first segment the images into superpixels by simple linear iterative clustering (SLIC), which can improve the efficiency and correctness of the progress. Then we calculate the reconstruction errors based on the initial background propagated from the boundaries of the image. We use a weighted sum of multi-scale region-level saliency as the pixel-level saliency in order to generate a more continuous and smooth result. Based on that, we further use object recognition as a vital prior to improve the performance of our method. Experimental results on three benchmark datasets show that the proposed method performed well to reach our expectations in terms of precision and recall.</description><subject>Biological system modeling</subject><subject>Computational modeling</subject><subject>Dictionaries</subject><subject>Encoding</subject><subject>Image reconstruction</subject><subject>Image segmentation</subject><subject>MI-KSVD</subject><subject>multi-scale</subject><subject>object location</subject><subject>Saliency</subject><subject>smoothing</subject><subject>Visualization</subject><issn>2325-5986</issn><issn>2325-5994</issn><isbn>9781467376587</isbn><isbn>1467376582</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2015</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo9j81Kw0AURkdRsNQ8QTcB14n3zp2_u5SqtVhxkeq2TGZuIFKrNAHp21uwuDpn9XE-pWYINSLw7XJ-99Osaw1oa09ojjxTBfuAxnnyzgZ_riaatK0ss7n49-CuVDEMHwCA7Fg7nqibJm572aVDmWWUNPZfu7KNg-TyKC_L6rl5v79Wl13cDlKcOFVvjw_r-VO1el0cY1ZVryGMVTSiKeTMpm2j6yKlKB2mbFvQkI1mtKQzJkGgFq1Hq2Nim8AYCkxCUzX72-1FZPO97z_j_rA5XaRfcOtA_Q</recordid><startdate>20150901</startdate><enddate>20150901</enddate><creator>Tianhao Shen</creator><creator>Jinqing Qi</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20150901</creationdate><title>Saliency detection based on MI-KSVD</title><author>Tianhao Shen ; Jinqing Qi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i208t-a4e238dd94bba6fa3caef1cd5b020d4291532d1ce103b157152ac95c0443893e3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Biological system modeling</topic><topic>Computational modeling</topic><topic>Dictionaries</topic><topic>Encoding</topic><topic>Image reconstruction</topic><topic>Image segmentation</topic><topic>MI-KSVD</topic><topic>multi-scale</topic><topic>object location</topic><topic>Saliency</topic><topic>smoothing</topic><topic>Visualization</topic><toplevel>online_resources</toplevel><creatorcontrib>Tianhao Shen</creatorcontrib><creatorcontrib>Jinqing Qi</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tianhao Shen</au><au>Jinqing Qi</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Saliency detection based on MI-KSVD</atitle><btitle>2015 IEEE 7th International Conference on Awareness Science and Technology (iCAST)</btitle><stitle>ICAwST</stitle><date>2015-09-01</date><risdate>2015</risdate><spage>25</spage><epage>30</epage><pages>25-30</pages><issn>2325-5986</issn><eissn>2325-5994</eissn><eisbn>9781467376587</eisbn><eisbn>1467376582</eisbn><abstract>In this paper, we propose a visual saliency detection algorithm with MI-KSVD, a codebook learning algorithm that balances reconstruction error and mutual incoherence of the codebook. We first segment the images into superpixels by simple linear iterative clustering (SLIC), which can improve the efficiency and correctness of the progress. Then we calculate the reconstruction errors based on the initial background propagated from the boundaries of the image. We use a weighted sum of multi-scale region-level saliency as the pixel-level saliency in order to generate a more continuous and smooth result. Based on that, we further use object recognition as a vital prior to improve the performance of our method. Experimental results on three benchmark datasets show that the proposed method performed well to reach our expectations in terms of precision and recall.</abstract><pub>IEEE</pub><doi>10.1109/ICAwST.2015.7314015</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2325-5986
ispartof 2015 IEEE 7th International Conference on Awareness Science and Technology (iCAST), 2015, p.25-30
issn 2325-5986
2325-5994
language eng
recordid cdi_ieee_primary_7314015
source IEEE Xplore All Conference Series
subjects Biological system modeling
Computational modeling
Dictionaries
Encoding
Image reconstruction
Image segmentation
MI-KSVD
multi-scale
object location
Saliency
smoothing
Visualization
title Saliency detection based on MI-KSVD
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T15%3A30%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Saliency%20detection%20based%20on%20MI-KSVD&rft.btitle=2015%20IEEE%207th%20International%20Conference%20on%20Awareness%20Science%20and%20Technology%20(iCAST)&rft.au=Tianhao%20Shen&rft.date=2015-09-01&rft.spage=25&rft.epage=30&rft.pages=25-30&rft.issn=2325-5986&rft.eissn=2325-5994&rft_id=info:doi/10.1109/ICAwST.2015.7314015&rft.eisbn=9781467376587&rft.eisbn_list=1467376582&rft_dat=%3Cieee_CHZPO%3E7314015%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i208t-a4e238dd94bba6fa3caef1cd5b020d4291532d1ce103b157152ac95c0443893e3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=7314015&rfr_iscdi=true