Image Fusion through Deep Convolutional Neural Network and Laplacian Pyramid
DOI:
https://doi.org/10.26438/ijcse/v6i3.403407Keywords:
Image Fusion, Deep Learning, Convolutional Neural Network, Laplacian PyramidAbstract
In the technically advanced world image fusion attracts as a considerable assistant for image processing experts. The role of image fusion in processing of images is robust by extracting the best and complementary features from two or more images and integrating that information by using appropriate algorithm in order to provide better recognition characteristics. Image fusion experts have been using images for a long time with machine learning algorithms. It requires very intensive pre-processing steps. Recently experts are very much interested in using long existing deep learning algorithms in processing the image data. This paper presents the deep convolutional neural network based image fusion using Laplacian pyramid method. Firstly the paper concentrates on the existing image fusion techniques and related work. Secondly on convolutional neural networks, deep learning and their features. Thirdly it presented the similarities among Convolutional Neural Network, Gaussian pyramid, Laplacian pyramid models. Lastly our proposed method and discussion on experimental results. It was observed that Deep Convolutional Neural Network and Laplacian pyramid based image fusion method gave better PSNR Values than the existing Laplacian Pyramid fusion methods for various images.
References
[1] A Goshtasby, S. Nikolov, Image Fusion: advances in the state of the art, Inf.Fusion 8(2) (2007) 114-118.
[2] S. Li, X.Kang, L. Fang,J.Hu,H.Yin, pixel-level image fusion: a survey of the state of the art, Inf. Fusion 33(2017)100-112.
[3]A review: Image Fusion Techniques and Applications by Mamta Sharma.
[4] Deep Learning for pixel-level image fusion: Recent advances and future prospects by Yu Liu, Xun Chen, Zengfu Wang, Z. Jane Wang, Rabab K. Ward, Xuesong Wang.
[5] Y. Liu, X.Chen, H. Peng, Z.Wang, Multi-focus image fusion with deep convolutional neural network, Inf. Fusion 36(2017) 191-207.
[6]B. Yang, J. Zhong Y.Li, Z.Chen, Multi-focus image fusion and super-resolution with convolutional neural network, Int. J. Wavelets Multiresolut.Inf. Process.15(4)(2017)1750037:1-15.
[7] C.Du, S.Gao, Image segmentation-based multi-focus image fusion through multi-scale convolutional neural network, IEEE access 5 (2017) 15750-15761.
[8] N. Kalantari, R. Ramamoorthi, Deep high dynamic range Of dynamic scenes, ACM Trans. Graph, 36 (4) (2017)144:1-12.
[9] Y.Liu, X.Chen, J. Cheng, H.Peng, A medical Image fusion method based on convolutional neural network, Proceedings of 20th International Conference on Information Fusion,(2017),pp.1-7.
[10] W. Huang, L. Xiao, Z. Wei, H. Liu, S.Tang, A new pan-sharpening method with deep neural networks, IEEE Geosci. Remote Sens. Lett.12(5)(2015)1037-1041.
[11] Z.Zhang, R. Blum, A categorization of multiscale-decomposition-based image fusion schemes with a performance study for a digital camera application, Proc. IEEE 87(8)(1999) 1315-1326.
[12] G. Piella, A general framework for multiresolution image fusion:from pixels to regions, Inf. Fusion 4 (4)(2003) 259-280.
[13] Implementation of Image Fusion algorithm using MATLAB(LAPLACIAN PYRAMID) by M. Pradeep,Assoc.Professor,ECE Dept,Shri Vishnu Engineering College for Women.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
