National Tsing Hua University Institutional Repository:Objective Quality Assessment for Image Retargeting Based on Structural Similarity
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 54367/62174 (87%)
Visitors : 14343068      Online Users : 37
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTHU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    NTHUR > College of Electrical Engineering and Computer Science > Department of Electrical Engineering > EE Journal / Magazine Articles  >  Objective Quality Assessment for Image Retargeting Based on Structural Similarity

    Please use this identifier to cite or link to this item:

    Title: Objective Quality Assessment for Image Retargeting Based on Structural Similarity
    Authors: Yuming Fang;Kai Zeng;Zhou Wang;Weisi Lin;Zhijun Fang;Chia-Wen Lin
    Teacher: 林嘉文
    Date: 2014
    Publisher: Institute of Electrical and Electronics Engineers
    Relation: IEEE Journal of Emerging and Selected Topics in Circuits and Systems, Institute of Electrical and Electronics Engineers, Volume 4, Issue 1, March 2014, Pages 95-105
    Keywords: Image quality assessment
    image retargeting
    image saliency
    structural similarity
    Abstract: We propose an objective quality assessment method for image retargeting. The key step in our approach is to generate a structural similarity (SSIM) map that indicates at each spatial location in the source image how the structural information is preserved in the retargeted image. A spatial pooling method employing both bottom-up and top-down visual saliency estimations is then applied to provide an overall evaluation of the retargeted image. To evaluate the performance of the proposed IR-SSIM algorithm, we created an image database that contains images produced by different retargeting algorithms and carried out subjective tests to assess the quality of the retargeted images. Our experimental results show that IR-SSIM is better correlated with subjective evaluations than existing methods in the literature. To further demonstrate the advantages and potential applications of IR-SSIM, we embed it into a multi-operator image retargeting process, which generates visually appealing retargeting results.
    Relation Link:
    Appears in Collections:[Department of Electrical Engineering] EE Journal / Magazine Articles
    [Center for Photonles Research ] CPR Journal / Magazine Articles

    Files in This Item:

    File Description SizeFormat


    SFX Query


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback