Advanced Image and Video Processing Using MATLAB by Shengrong Gong & Chunping Liu & Yi Ji & Baojiang Zhong & Yonggang Li & Husheng Dong

Author:Shengrong Gong & Chunping Liu & Yi Ji & Baojiang Zhong & Yonggang Li & Husheng Dong
Language: eng
Format: epub
ISBN: 9783319772233
Publisher: Springer International Publishing

Then we take Mallat fast algorithm wavelet transform as an example to fuse the two modal images. Firstly, the two images are decomposed by wavelet, and the fusion rule based on combination of selection and weighting factor is adopted for the low-frequency part of the decomposed image, then, for the high frequency part, the fusion rule based on regional energy is adopted. Finally, the fusion image is obtained by inverse wavelet transform.

For the multiscale wavelet decomposition of the image, 4 different subgraphs can be obtained at each decomposition scale. LL is the low-frequency part, which represents the main information of the image and concentrates the majority of the energy of the image. While HL, LH and HH are the high frequency parts, which represent the details of the horizontal direction, vertical direction and diagonal direction of the image respectively. In terms of fusion rules, different fusion rules are adopted for high frequency and low frequency components respectively. Since the low-frequency component LL of the multi-scale decomposed image has a great influence on the quality of the restoration image. Thus, the combination of the selection and the weighting factors is used in the fusion of low frequency components.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.