Image fusion using two symmetric exposed images in the JPEG stream

Geun Young Lee, Sung Hak Lee, Hyuk Ju Kwon, Kyu Ik Sohng

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

1 Scopus citations

Abstract

The objective of fusing differently exposed images is to well represent the luminance information of the scene in a single image. In order to fuse multi exposure images, it is necessary to determine overexposed or underexposed areas in each of the captured images using an activity measure which extracts image features. In this paper, we presents image fusion using two symmetric exposed images in the JPEG stream. We find out that the AC coefficients after the quantization in JPEG baseline can describe local image features in the image block. Based on a maximum selection rule, a proposed image fusion is conducted by the comparison of the AC coefficients after the quantization instead of activity measures which need additional computations. This simple method allows multi exposure images to quickly combine a single image in JPEG baseline, therefore, it can be embedded in resource limited imaging platform such as a surveillance system.

Original languageEnglish
Title of host publicationProceedings of the 2016 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2016
EditorsHamid R. Arabnia, Leonidas Deligiannidis, Fernando G. Tinetti, Jane You, George Jandieri, George Jandieri, Iakov Korovin, Gerald Schaefer, Kok Swee Sim, Ashu M. G. Solo
PublisherCSREA Press
Pages341-342
Number of pages2
ISBN (Electronic)1601324421, 9781601324429
StatePublished - 2016
Event2016 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2016 - Las Vegas, United States
Duration: 25 Jul 201628 Jul 2016

Publication series

NameProceedings of the 2016 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2016

Conference

Conference2016 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2016
Country/TerritoryUnited States
CityLas Vegas
Period25/07/1628/07/16

Keywords

  • Image fusion
  • JPEG
  • Multi exposure images
  • Resource limited imaging platform

Fingerprint

Dive into the research topics of 'Image fusion using two symmetric exposed images in the JPEG stream'. Together they form a unique fingerprint.

Cite this