School of Physics and Optoelectronic Engineering, Xidian University, Xi'an 710071, China.
Sensors (Basel). 2018 Dec 6;18(12):4299. doi: 10.3390/s18124299.
The presence of stripe nonuniformity severely degrades the image quality and affects the performance in many infrared (IR) sensing applications. Prior works correct the nonuniformity by using similar spatial representations, which inevitably damage some detailed structures of the image. In this paper, we instead take advantage of spectral prior of stripe noise to solve its correction problem in single IR image. We first analyse the significant spectral difference between stripes and image structures and utilize this knowledge to characterize stripe nonuniformity. Then a two-stage filtering strategy is adopted combining spectral and spatial filtering. The proposed method enables stripe nonuniformity to be eliminated from coarse to fine, thus preserving image details well. Extensive experiments on simulated images and raw IR images demonstrate that the proposed method achieves superior correction performance over the recent state-of-the-art methods.
条纹非均匀性的存在严重降低了图像质量，并影响了许多红外（IR）感应应用中的性能。先前的工作通过使用相似的空间表示来校正非均匀性，这不可避免地会损坏图像的一些细节结构。在本文中，我们转而利用条纹噪声的光谱先验来解决单幅红外图像中的校正问题。我们首先分析条纹和图像结构之间的显著光谱差异，并利用这一知识来描述条纹非均匀性。然后采用结合光谱和空间滤波的两阶段滤波策略。所提出的方法能够从粗到细地消除条纹非均匀性，从而很好地保留图像细节。对模拟图像和原始红外图像的广泛实验表明，所提出的方法在最近的最先进方法中实现了卓越的校正性能。
