A Fractional Total Variational CNN Approach for SAR Image Despeckling

Synthetic aperture radar (SAR) image despeckling is an essential problem in remote sensing technology, which has a strong influence on the performance of the following processing. We propose a new despeckled algorithm combining CNN and fractional-order total variation. Through constructing a CNN mod...

Full description

Saved in:
Bibliographic Details
Published inIntelligent Computing Methodologies Vol. 10956; pp. 431 - 442
Main Authors Bai, Yu-Cai, Zhang, Sen, Chen, Miao, Pu, Yi-Fei, Zhou, Ji-Liu
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2018
Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
Despeckling
Fractional differential
Image denoising
Synthetic aperture radar (SAR)
Online AccessGet full text

Cover

More Information
Summary:Synthetic aperture radar (SAR) image despeckling is an essential problem in remote sensing technology, which has a strong influence on the performance of the following processing. We propose a new despeckled algorithm combining CNN and fractional-order total variation. Through constructing a CNN model and introducing the fractional-order total variation into loss function as the regularization term, the experimental results prove that our proposed method can avoid detail ambiguity and overly smooth caused by integral-order, and preserve rich texture and details information. Therefore, the high-quality despeckled images generated by our model will significantly improve the availability of SAR images.
ISBN:3319959565
9783319959566
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-95957-3_46