Content-Based cropping using visual saliency and blur detection

Yung Chieh Chou, Chih Yun Fang, Po Chyi Su, Yu Chien Chien

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

This research presents an automatic image/frame cropping scheme to preserve the regions of interest in imagery data. First, a blur detection based on Structural Similarity (SSIM) is proposed to identify whether an image contains a blurred background and the sharp foreground objects can then be extracted. The visual saliency is further calculated to help remove insignificant boundaries. Some pre-defined rules are employed to determine more appropriate cropping limits. If further reduction of resolution is necessary, the resulting image after cropping will be scaled directly to the target size. The experimental results show that the proposed method is computationally efficient and the promising results can be achieved in still images and video frames.

Original languageEnglish
Title of host publicationUbi-Media 2017 - Proceedings of the 10th International Conference on Ubi-Media Computing and Workshops with the 4th International Workshop on Advanced E-Learning and the 1st International Workshop on Multimedia and IoT
Subtitle of host publicationNetworks, Systems and Applications
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538627617
DOIs
StatePublished - 18 Oct 2017
Event10th International Conference on Ubi-Media Computing and Workshops, Ubi-Media 2017 - Pattaya, Thailand
Duration: 1 Aug 20174 Aug 2017

Publication series

NameUbi-Media 2017 - Proceedings of the 10th International Conference on Ubi-Media Computing and Workshops with the 4th International Workshop on Advanced E-Learning and the 1st International Workshop on Multimedia and IoT: Networks, Systems and Applications

Conference

Conference10th International Conference on Ubi-Media Computing and Workshops, Ubi-Media 2017
Country/TerritoryThailand
CityPattaya
Period1/08/174/08/17

Keywords

  • blur detection
  • content-based cropping
  • retargeting
  • saliency
  • SSIM

Fingerprint

Dive into the research topics of 'Content-Based cropping using visual saliency and blur detection'. Together they form a unique fingerprint.

Cite this