Open AccessMulti‐exposure image fusion based on feature evaluation with adaptive factor
Author(s) -
Huang Li,
Li Zhengping,
Xu Chao,
Feng Bo
Publication year - 2021
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/ipr2.12317
Subject(s) - artificial intelligence , fusion , computer vision , computer science , feature (linguistics) , image fusion , pyramid (geometry) , image (mathematics) , window (computing) , sliding window protocol , pattern recognition (psychology) , image quality , texture (cosmology) , mathematics , philosophy , linguistics , geometry , operating system
The authors present a new multi‐exposure images fusion method based on feature evaluation with adaptive factor. It is noticed the existing multi‐exposure fusion algorithm is not well adapted to the input images, which are overall bright or dark, the fused image quality is not pretty good, and the details are not preserved completely. So an adaptive factor to adapt the intensity of input images is presented here. First, the exposure assessment weight, texture change weight, and colour intensity weight are calculated by a sliding window. Finally, the images are fused by using a pyramid to avoid the seams. Twenty exposure input images of different scenes are selected, the subjective and objective aspects are analysed and compared with several existing multi‐exposure image fusion methods. The experimental results show that the proposed method can retain more details and obtain satisfactory visual effects on static scenes.