A hybrid nonlinear and linear approach for content-aware image downscaling

Takumi Owada, Yusuke Kameda, Ichiro Matsuda, Susumu Itoh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Seam carving and its variants are popular as content-aware image resizing methods. However, they often suffer from the problem that excessive downscaling causes perceptually annoying distortions. This is mainly because penetration of the seams into some important objects becomes unavoidable at the latter stage of the processing. As a solution for this problem, we previously proposed a nonlinear downscaling technique which iteratively performed a DCT-based locally linear scaling operator within 'belt-like seams', i.e. seams with a certain width. To enhance this idea, in this paper, we replace the latter processing stage with a global linear scaling operator. A transition point between the nonlinear and linear processing stages is automatically determined based on a preservation measurement for the important objects. Simulation results show that our approach can produce subjectively better results than the conventional nonlinear downscaling methods.

Original languageEnglish
Title of host publicationInternational Workshop on Advanced Imaging Technology, IWAIT 2020
EditorsPhooi Yee Lau, Mohammad Shobri
PublisherSPIE
ISBN (Electronic)9781510638358
DOIs
Publication statusPublished - 1 Jan 2020
EventInternational Workshop on Advanced Imaging Technology, IWAIT 2020 - Yogyakarta, Indonesia
Duration: 5 Jan 20207 Jan 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11515
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceInternational Workshop on Advanced Imaging Technology, IWAIT 2020
CountryIndonesia
CityYogyakarta
Period5/01/207/01/20

Keywords

  • Content-aware image resizing
  • Linear downscaling
  • Object detection
  • Seam carving
  • Segmentation

Fingerprint Dive into the research topics of 'A hybrid nonlinear and linear approach for content-aware image downscaling'. Together they form a unique fingerprint.

  • Cite this

    Owada, T., Kameda, Y., Matsuda, I., & Itoh, S. (2020). A hybrid nonlinear and linear approach for content-aware image downscaling. In P. Y. Lau, & M. Shobri (Eds.), International Workshop on Advanced Imaging Technology, IWAIT 2020 [115150X] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11515). SPIE. https://doi.org/10.1117/12.2567020