Repository logo
  • English
  • العربية
  • বাংলা
  • Català
  • Čeština
  • Deutsch
  • Ελληνικά
  • Español
  • Suomi
  • Français
  • Gàidhlig
  • हिंदी
  • Magyar
  • Italiano
  • Қазақ
  • Latviešu
  • Nederlands
  • Polski
  • Português
  • Português do Brasil
  • Srpski (lat)
  • Српски
  • Svenska
  • Türkçe
  • Yкраї́нська
  • Tiếng Việt
Log In
New user? Click here to register.Have you forgotten your password?
  1. Home
  2. Scholalry Output
  3. Publications
  4. Saliency and memorability driven retargeting
 
  • Details

Saliency and memorability driven retargeting

Source
2016 International Conference on Signal Processing and Communications Spcom 2016
Date Issued
2016-11-16
Author(s)
Patel, Diptiben
Raman, Shanmuganathan  
DOI
10.1109/SPCOM.2016.7746665
Abstract
Wide range of display devices led to the requirement of resizing an image by preserving important information of an image. Image retargeting is the process of changing the size or aspect ratio of an image according to the target display size. The motive of the proposed approach is to remove or add a seam (making a single pixel path from top to bottom or left to right) in order to change the image size. By iteratively removing or adding lowest energy seams, size or aspect ratio of an image can be changed. The proposed image retargeting approach makes use of a combination of global (saliency, memorability) and local (corner measure) energy measures in order to define energy contribution of a pixel. Quantitative assessment of the proposed approach is carried out by a recent quality assessment metric which makes use of global geometric structures and local pixel correspondences. We show that the proposed approach is able to achieve state-of-the-art results for various types of natural images.
Unpaywall
URI
https://d8.irins.org/handle/IITG2025/21807
IITGN Knowledge Repository Developed and Managed by Library

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science

  • Privacy policy
  • End User Agreement
  • Send Feedback
Repository logo COAR Notify