Journal
MULTIMEDIA TOOLS AND APPLICATIONS
Volume 78, Issue 24, Pages 34483-34512Publisher
SPRINGER
DOI: 10.1007/s11042-019-08070-6
Keywords
Multifocus image fusion; Convolutional neural network; Discrete wavelet transform
Categories
Funding
- National Science AMP
- Technology Pillar Program of China [2012BAH48F02]
- National Natural Science Foundation of China [61801190]
- Nature Science Foundation of Jilin Province [20180101055JC]
- Outstanding Young Talent Foundation of Jilin Province [20180520029JH]
- China Postdoctoral Science Foundation [2017M611323]
- Industrial Technology Research and Development Funds of Jilin province [2019C054-3]
- Fundamental Research Funds for the Central Universities, JLU
Ask authors/readers for more resources
In this paper, a novel multifocus image fusion algorithm based on the convolutional neural network (CNN) in the discrete wavelet transform (DWT) domain is proposed. The algorithm combines the advantages of spatial domain- and transform domain-based methods. The CNN is used to amplify features and generate different decision maps for different frequency subbands instead of image blocks or source images. In addition, the CNN, which can be seen as an adaptive fusion rule, replaces the traditional fusion rules. The proposed algorithm includes the following steps: first, we decompose each source image into one low frequency subband and several high frequency subbands using the DWT; second, these frequency subbands are used as input to the CNN to generate weight maps. To obtain a more accurate decision map, it is refined by a series of postprocessing operations, including the sum-modified-Laplacian (SML) and guided filter (GF). According to their decision maps, the frequency subbands are fused; finally, the fused image can be obtained using the inverse DWT. The experimental results show that our algorithm is superior to other algorithms.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available