In Synthetic Aperture Radar (SAR) imaging, despeckling is very important for image analysis,whereas speckle is known as a kind of multiplicative noise caused by the coherent imaging system. During the past three decades, various algorithms have been proposed to denoise the SAR image. Generally, the BM3D is considered as the state of art technique to despeckle the speckle noise with excellent performance. More recently, deep learning make a success in image denoising and achieved a improvement over conventional method where large train dataset is required. Unlike most of the images SAR image despeckling approach, the proposed approach learns the speckle from corrupted images directly. In this paper, the limited scale of dataset make a efficient exploration by using convolutioal denoising autoencoder (C-DAE) to reconstruct the speckle-free SAR images. Batch normalization strategy is integrated with C- DAE to speed up the train time. Moreover, we compute image quality in standard metrics, PSNR and SSIM. It is revealed that our approach perform well than some others.
翻译:在合成孔径雷达(SAR)成像中,脱光对于图像分析非常重要,因为光谱被称作由连贯成像系统产生的一种多复制噪音。在过去三十年中,提出了各种算法,以隐蔽合成孔径雷达图像。一般而言,BM3D被认为是以出色性能破碎闪光噪音的先进技术。最近,深层学习在图像脱光方面取得成功,并取得了与常规方法相比的改进,而常规方法需要大型列车数据集。与大多数图像SAR图像脱光方法不同,拟议方法直接从腐烂的图像中学习光谱。在本文中,有限的数据集规模使得通过使用光谱脱色自动电解码(C-DAE)来重建无孔径雷达图像来进行有效探索。Batch正常化战略与C-DAE相结合,以加快列车时间。此外,我们在标准指标、PSNR和SSIM中计算了图像质量。它揭示了我们的方法比其他一些方法表现得要好。